Note: Descriptions are shown in the official language in which they were submitted.
DYNAMIC MONITORING AND PROFILING OF DATA EXCHANGES WITHIN AN
ENTERPRISE ENVIRONMENT
TECHNICAL FIELD
[001] The disclosed embodiments generally relate to computer-implemented
systems and processes that dynamically monitor and profile exchanges of data
between
network-connected devices and systems within an enterprise environment.
BACKGROUND
[002] Today, consumers are comfortable interacting with financial institutions
across channels of digital communication, especially as these consumers
continue to
integrate technology into aspects of their daily lives. Many financial
institutions,
however, fail to leverage these digital channels of communication and the
potential
mechanisms for digital interaction to improve a provisioning of financial
services to
customers while reducing a risk that results from these provisioned financial
services.
SUMMARY
[003] In some examples, an apparatus includes a communications unit, a
storage unit storing instructions, and at least one processor coupled to the
communications unit and the storage unit. The at least one processor is
configured to
execute the instructions to obtain information associated with a first
counterparty to an
exchange of data. The data exchange is characterized by at least one parameter
value,
and based the obtained information, the at least one processor is further
configured to
determine a value of a metric characterizing a probability that the first
counterparty
performs the data exchange in accordance with the at least one parameter value
during
a future temporal interval. The at least one processor is also configured to
establish a
1
CA 3019195 2018-10-01
consistency between a triggering criterion associated with the data exchange
and at
least one of (i) the metric value, (ii) a change in the metric value during a
prior temporal
interval, or (iii) interaction data that characterizes an interaction between
the first
counterparty and a second counterparty to the data exchange. Further, and in
response to the established consistency, the at least one processor is further
configured
to generate and transmit, via the communications unit, a first signal to a
first device.
The first signal includes additional information that causes a first
application program
executed by the first device to present a representation of the metric value
within a
corresponding digital interface.
[004] In other examples, a computer-implemented method includes obtaining,
by at least one processor, information associated with a first counterparty to
an
exchange of data. The data exchange is characterized by at least one parameter
value,
and based the obtained information, the computer-implemented method
determines, by
the at least one processor, a value of a metric characterizing a probability
that the first
counterparty performs the data exchange in accordance with the at least one
parameter
value during a future temporal interval. The computer-implemented method also
includes establishing, by the at least one processor, a consistency between a
triggering
criterion associated with the data exchange and at least one of (i) the metric
value, (ii) a
change in the metric value during a prior temporal interval, or (iii)
interaction data that
characterizes an interaction between the first counterparty and a second
counterparty to
the data exchange. In response to the established consistency, the computer-
implemented method generates and transmits, by the at least one processor, a
first
signal to a first device. The first signal includes additional information
that causes a first
2
CA 3019195 2018-10-01
application program executed by the first device to present a representation
of the
metric value within a corresponding digital interface.
[005] Additionally, in some examples, a tangible, non-transitory computer-
readable medium stores instructions that, when executed by at least one
processor,
cause the at least one processor to perform a method. The method includes
obtaining
information associated with a first counterparty to an exchange of data. The
data
exchange is characterized by at least one parameter value, and based the
obtained
information, the method determines a value of a metric characterizing a
probability that
the first counterparty performs the data exchange in accordance with the at
least one
parameter value during a future temporal interval. The method also includes
establishing a consistency between a triggering criterion associated with the
data
exchange and at least one of (i) the metric value, (ii) a change in the metric
value during
a prior temporal interval, or (iii) interaction data that characterizes an
interaction
between the first counterparty and a second counterparty to the data exchange.
In
response to the established consistency, the method generates and transmits a
signal
to a device. The signal includes additional information that causes an
application
program executed by the device to present a representation of the metric value
within a
corresponding digital interface.
[006] It is to be understood that both the foregoing general description and
the
following detailed description are exemplary and explanatory only and are not
restrictive
of the invention, as claimed. Further, the accompanying drawings, which are
incorporated in and constitute a part of this specification, illustrate
aspects of the
present disclosure and together with the description, serve to explain
principles of the
disclosed embodiments as set forth in the accompanying claims.
3
CA 3019195 2018-10-01
BRIEF DESCRIPTION OF THE DRAWINGS
[007] FIG. 1 is a diagram of an exemplary computing environment, consistent
with disclosed embodiments.
[008] FIG. 2 is a diagram illustrating a portion of an exemplary computing
environment, consistent with the disclosed embodiments.
[009] FIG. 3A is a diagram illustrating an exemplary multidimensional metric-
value coordinate space, consistent with the disclosed embodiments.
[010] FIGs. 3B, 3C, and 3D are diagrams illustrating an exemplary
multidimensional risk coordinate space, consistent with the disclosed
embodiments.
[011] FIG. 4A is a diagram illustrating a portion of an exemplary computing
environment, consistent with the disclosed embodiments.
[012] FIG. 4B is a diagram illustrating an exemplary element of structured
exception data, consistent with the disclosed embodiments.
[013] FIG. 4C is a diagram illustrating a portion of an exemplary computing
environment, consistent with the disclosed embodiments.
[014] FIGs. 4D and 5 are diagrams illustrating portions of an exemplary
graphical user interface, consistent with the disclosed embodiments.
[015] FIG. 6 is a flowchart of an exemplary process for monitoring and
profiling
exchanges of data within an enterprise environment, consistent with the
disclosed
embodiments.
DETAILED DESCRIPTION
[016] Reference will now be made in detail to the disclosed embodiments,
examples of which are illustrated in the accompanying drawings. The same
reference
numbers in the drawings and this disclosure are intended to refer to the same
or like
elements, components, and/or parts.
4
CA 3019195 2018-10-01
[017] In this application, the use of the singular includes the plural unless
specifically stated otherwise. In this application, the use of "or" means
"and/or" unless
stated otherwise. Furthermore, the use of the term "including," as well as
other forms
such as "includes" and "included," is not limiting. In addition, terms such as
"element" or
"component" encompass both elements and components comprising one unit, and
elements and components that comprise more than one subunit, unless
specifically
stated otherwise. Additionally, the section headings used herein are for
organizational
purposes only, and are not to be construed as limiting the described subject
matter.
I. Exemplary Computing Environments
[018] FIG. 1 is a diagram illustrating an exemplary computing environment 100,
consistent with certain disclosed embodiments. As illustrated in FIG. 1,
environment
100 may include one or more devices, such as client device 102 (e.g., as
operated by
user 101) and client device 122 (e.g., as operated by user 121), and one or
more
computing systems, such as monitoring system 130, each of which may be
interconnected through any appropriate combination of communications networks,
such
as network 120. Examples of network 120 include, but are not limited to, a
wireless
local area network (LAN), e.g., a "Wi-Fi" network, a network utilizing radio-
frequency
(RF) communication protocols, a Near Field Communication (NFC) network, a
wireless
Metropolitan Area Network (MAN) connecting multiple wireless LANs, and a wide
area
network (WAN), e.g., the Internet.
[019] In some examples, client device 102 may include a computing device
having one or more tangible, non-transitory memories that store data and/or
software
instructions, and one or more processors, e.g., processor 104, configured to
execute
the software instructions. The one or more tangible, non-transitory memories
may, in
CA 3019195 2018-10-01
some instances, store software applications, application modules, and other
elements of
code executable by the one or more processors, e.g., within application
repository 106.
For example, as illustrated in FIG. 1, client device 102 may maintain, within
application
repository 106, one or more executable applications associated with, and
provisioned to
client device 102 by, monitoring system 130, such as, but not limited to,
banking
application 108 or monitoring application 110. As described herein, each of
banking
application 108 and monitoring application 110 may exchange data with
monitoring
system 130 or other network-connected computing systems operating within
environment 100 through one or more secure, programmatic interfaces, such as
an
application programming interfaces (API), e.g., in support of any of the
exemplary
processes described herein.
[020] Client device 102 may also establish and maintain, within the one or
more
tangible, non-tangible memories, one or more structured or unstructured data
repositories or databases, e.g., data repository 111, that include device data
112 and
application data 114. For example, device data 112 may include data that
uniquely
identifies client device 102, such as a media access control (MAC) address of
client
device 102 or an IP address assigned to client device 102, and application
data 114
may include information that facilitates a performance of operations by the
one or more
executable application programs maintained within application repository 106,
e.g.,
banking application 108 and/or monitoring application 110. For instance,
application
data 114 may include one or more authentication credentials that enable user
101 to
access one or more digital interfaces generated by executed banking
application 108
and additionally, or alternatively, monitoring application 110, and examples
of the one or
more authentication credentials include, but are not limited to, an
alphanumeric user
6
CA 3019195 2018-10-01
name or user name, an alphanumeric password, or a biometric authentication
credential
(e.g., a digital image of user 101's face, a fingerprint scan, etc.).
[021] Client device 102 may also include a display unit 116A configured to
present interface elements to user 101, and an input unit 116B configured to
receive
input from user 101, e.g., in response to the interface elements presented
through
display unit 116A. By way of example, display unit 116A may include, but is
not limited
to, an LCD display unit or other appropriate type of display unit, and input
unit 116B
may include, but is not limited to, a keypad, keyboard, touchscreen, voice
activated
control technologies, or appropriate type of input unit. Further, in
additional aspects (not
depicted in FIG. 1), the functionalities of display unit 116A and input unit
116B may be
combined into a single device, e.g., a pressure-sensitive touchscreen display
unit that
presents interface elements and receives input from user 101. Client device
102 may
also include a communications unit 116C, such as a wireless transceiver
device,
coupled to processor 104 and configured by processor 104 to establish and
maintain
communications with network 120 using any of the communications protocols
described
herein.
[022] Examples of client device 102 may include, but are not limited to, a
personal computer, a laptop computer, a tablet computer, a notebook computer,
a
hand-held computer, a personal digital assistant, a portable navigation
device, a mobile
phone, a smartphone, a wearable computing device (e.g., a smart watch, a
wearable
activity monitor, wearable smart jewelry, and glasses and other optical
devices that
include optical head-mounted displays (OHMDs)), an embedded computing device
(e.g., in communication with a smart textile or electronic fabric), and any
other type of
computing device that may be configured to store data and software
instructions,
7
CA 3019195 2018-10-01
execute software instructions to perform operations, and/or display
information on an
interface module, consistent with disclosed embodiments. In some instances,
user 101
may operate client device 102 and may do so to cause client device 102 to
perform one
or more operations consistent with the disclosed embodiments.
[023] Further, although not illustrated in FIG. 1, client device 122 may also
include a computing device having one or more tangible, non-transitory
memories that
store data and/or software instructions, and one or more processors configured
to
execute the software instructions. As described herein, the one or more
tangible, non-
transitory memories may store software applications, application modules, and
other
elements of code executable by the one or more processors (e.g., banking
application
108 and/or monitoring application 110), and may include one or more structures
or
structured or unstructured data repositories, such as those described herein
that
maintain data characterizing client device 122 or user 101 and the executable
application programs. It should be understood that, unless otherwise
indicated, these
and other exemplary components of client device 122 are similar in structure
and
functionality to those described herein in reference to client device 102.
Further, the
description of user 101, as set forth below, may also apply to user 121 and to
operators
of other client devices within environment 100.
[024] Referring back to FIG. 1, monitoring system 130 may represent a
computing system that includes one or more servers (not depicted in FIG. 1)
and
tangible, non-transitory memory devices storing executable code and
application
modules. Further, the servers may each include one or more processor-based
computing devices, which may be configured to execute portions of the stored
code or
application modules to perform operations consistent with the disclosed
embodiments.
8
CA 3019195 2018-10-01
[025] In other examples, monitoring system 130 may correspond to a distributed
system that includes computing components distributed across one or more
networks,
such as network 120, or other networks, such as those provided or maintained
by cloud-
service providers, e.g., Google CloudTM, Microsoft AzureTM, etc. In some
instances, and
as described herein, the distributed computing components of monitoring system
130
may collectively perform operations that establish and maintain one or more
cloud-
based data repositories that maintain, among other things, data identifying
and
characterizing one or more counterparties to an exchange of data (e.g.,
counterparty
data) and data identifying and characterizing one or more prior exchanges of
data
involving the one or more counterparties (e.g., transaction data).
[026] In other instances, also described herein, the distributed computing
components of monitoring system 130 may collectively perform additional, or
alternate,
operations that establish an artificial neural network capable of, among other
things,
adaptively and dynamically processing portions of the counterparty and/or
transaction
data to predict a value of a metric characterizing a probability that a
corresponding one
of the of the counterparties performs the data exchange in accordance with at
least one
parameter value during a future temporal interval. The disclosed embodiments
are,
however, not limited to these exemplary distributed systems, and in other
instances,
monitoring system 130 may include computing components disposed within any
additional or alternate number or type of computing systems or across any
appropriate
network.
[027] By way of example, monitoring system 130 may be associated with, or
may be operated by, a financial institution that provides financial services
to customers.
In one instance, the customers of the financial institution can include one or
more
9
CA 3019195 2018-10-01
individuals (e.g., user 101 or user 121), and the financial institution can
provide personal
financial services to the one or more individual customers that include, but
are not
limited to, issuing and maintaining deposit accounts (e.g., checking accounts,
savings
accounts, etc.), issuing personal credit cards or other personal lines of
credit, or
underwriting, holding, or services personal loans or mortgages. In other
instances, the
customers of the financial institution can also include one or more business
operating in
corresponding jurisdictions and having corresponding corporate structures
(e.g., one or
more "commercial" customers). As described herein, the financial institution
can
provide financial services to these commercial customers that include, but are
not
limited to, issuing and maintaining deposit accounts (e.g., commercial
checking
accounts), issuing commercial credit cards or revolving lines of credit,
providing
transactions services (e.g., payment processing), or underwriting, holding, or
services
commercial loans.
[028] In some instances, the terms that characterize the provided financial
services, and a risk to the financial institution that results from the
provision of these
financial services, can depend not only on an initial credit worthiness of the
personal or
commercial customers of the financial institution (e.g., at an issuance of a
credit card,
revolving line of credit, commercial loan, etc.), but also on a subsequent
behavior of and
additional actions taken by these personal and commercial customers. In some
instances, monitoring system 130 can perform any of the exemplary processes
described herein to apply one or more predictive models to data that
identifies and
characterizes the customers of the financial institution, and based on the
application of
the predictive models, monitoring system can generate a composite metric value
CA 3019195 2018-10-01
indicative of the risk, to the financial institution, resulting from the
subsequent behavior
of and additional actions taken by each of the one or more customers.
[029] Monitoring system 130 may also perform operations that parameterize a
risk profile for each of the one or more customers based not only on the
corresponding
predicted value of the composite metric, but also on a derived temporal
variation in each
of the predicted values of the composite metric and additionally, or
alternatively, on
values of other parameters that characterize the customers, the financial
services
provided to the customers, or a relationship between the customers and the
financial
institution. In some instances, as described herein, the parameterized risk
profile for a
corresponding one of the customers, such as a commercial customer of the
financial
institution, can trigger an automatic performance, by monitoring system 130 of
one or
more operations associated with the commercial customer or the financial
services
provided to that commercial customer. Examples of these triggered operations
can
include, but are not limited to, a generation and a delivery of a programmatic
notification
to one or more network-connected devices or systems operating within
environment
100, such as client devices 102 or 122, or a dynamically review or
modification of the
terms that characterize the provided financial services.
[030] To facilitate the performance of any of the exemplary processes
described
herein, monitoring system 130 may maintain, within one or more tangible, non-
transitory
memories, a customer database 132, a transaction database 134, an account
database
135, and a monitoring database 136. By way of example, customer database 132
may
include data records that identify and characterize users of one or more
native
application programs associated with, or supported by, monitoring system 130,
such as
banking application 108 executed by client devices 102 or 122. In some
instances,
11
CA 3019195 2018-10-01
each of these users may correspond to a customer of the financial institution
that
operates monitoring system 130, which may provide any of the exemplary
banking,
lending, or financial services to these customers.
[031] In some examples, the data records of customer database 132 may
include, for each of the users, a corresponding user identifier (e.g., an
alphanumeric
login name associated with executed monitoring application 110) and a
corresponding
unique device identifier associated with each network-connected device or
system
operated by that user (e.g., an IP address, a MAC address, a mobile telephone
number,
etc.). Further, and as described herein, the data records of customer database
132
may also maintain information that identifies and characterizes each of the
customers of
the financial institution that operates monitoring system 130, such as, but
not limited to,
the individual and commercial customers described herein. For example, and for
a
particular one of the customers, the data records of customer database 132 may
include
a unique identifier of the customer (e.g., a customer name, an alphanumeric
customer
identifier, etc.), data specifying a physical address of the customer, and
profile data that
characterizes the customer and a relationship between the customer and the
financial
institution.
[032] By way of example, and as described herein, the customers of the
financial institution may include one or more individual customers, such as
user 101 or
user 121. In some instances, and for each of these individual customers, the
profile
data maintained within customer database 132 may include, but is not limited
to, values
of demographic parameters that characterize the individual customer (e.g., an
age, a
gender, an occupation, a family structure, etc.) and information
characterizing a current
or historical relationship between that customer and the financial
institution.
12
CA 3019195 2018-10-01
[033] In other examples, also described herein, the customers of the financial
institution may include one or more commercial customers, and the profile data
maintained within customer database 132 may include, for each of the
commercial
customers, information that identifies a current or historical organizational
structure of
that commercial customer (e.g., an incorporated entity, a limited-liability
partnership,
etc.) and a jurisdiction in which the commercial customer is incorporated or
registered.
The profile data for each of the commercial customers may also identify and
characterizing various operations performed by the commercial customer, e.g.,
as
specified by a four-digit, standard industrial classification (SIC) code
assigned to or
associated with that particular commercial customer and additionally, or
alternatively, a
financial position of the commercial customer. For instance, and for a
particular one or
the commercial customers, the profile data may include, among other things,
data
characterizing earnings, assets, liabilities, or net (or gross) sales of the
particular
commercial customers across one or more reporting periods (e.g., based on
quarterly
reports, yearly reports, or tax returns generated for submission to one or
more
governmental or regulatory entities).
[034] Further, and as described herein, one or more of the users of banking
application 108, e.g., user 101 or user 121, may be associated with, may
represent, or
may be employed by one or more of the commercial customers of the financial
institution. In some instances, the data records of the customer database 132
may
associate or link the information identifying each of these users (e.g., the
user and
device identifiers described herein) to corresponding elements of commercial
customer
data 132A, as described herein. The disclosed embodiments are, however, not
limited
to these examples of customer-specific data, and in other instances, the data
records of
13
CA 3019195 2018-10-01
customer database 132 may include any additional or alternate elements of the
profile
data described herein, and further, any additional or alternate information
capable of
identifying or characterizing the individual or commercial customers of the
financial
institution.
[035] Referring back to FIG. 1, transaction database 134 may include data
records that identify and characterize one or more exchanges of data initiated
by, or on
behalf of, one or more users of monitoring system 130 during prior temporal
intervals.
For example, and for a corresponding one of the initiated data exchanges, the
data
records of transaction database 134 may include, but are not limited to, a
unique
identifier of the initiated data exchange, data that identifies the initiating
user, device, or
customer (e.g., the login credential of user 101, the device identifier of
client device 102,
one of the customer identifiers described herein, etc.), an initiation time or
date, and
values of one or more parameters that characterize the corresponding one of
the
initiated data exchanges, as described herein.
[036] By way of example, one or more of the initiated exchanges of data may
correspond to a purchase transaction involving a payment instrument (e.g., a
credit card
account, a debit card account linked to an underlying deposit account, etc.)
issued to a
commercial customer of the financial institution that operated monitoring
system. In
some instances, the data records of transaction database 134 may maintain, for
the
initiated purchase transaction, parameter values that include an identifier of
the
payment instrument (e.g., a portion of a tokenized account number, etc.), a
transaction
amount, a transaction date or time, a counterparty identifier (e.g., a
merchant name or
identifier), and data indicative of a purchased product or service (e.g., a
universal
product code (UPC), etc.).
14
CA 3019195 2018-10-01
[037] In other examples, one or more of the initiated exchanges of data may
facilitate an issuance of a revolving line of credit, a commercial loan, a
payment
instrument or other financial, credit, or payment instrument to a commercial
customer of
the financial institution that operates monitoring system 130. In some
instances, the
data records of transaction database 134 may include, for each of the issued
financial,
credit, or payment instruments, data that identifies the financial, credit, or
payment
instrument, a time or date of issuance, and a value of one or more parameters
that
characterize the financial, credit, or payment instrument, such as, but not
limited to, an
amount of available credit or a corresponding repayment schedule.
[038] Further, in some examples, one or more of the initiated exchanges of
data may also correspond to a transaction initiated by a commercial customer
in
furtherance of a repayment schedule associated with any of the financial,
credit, or
payment instruments described herein, e.g., as issued by the financial
institution that
operates monitoring system 130 or by other financial institutions. For
instance, the data
records of transaction database 134 may include, for each of these repayment
transactions, a corresponding transaction identifier, a transaction amount, a
transaction
data or time, an identifier of the corresponding one of the financial, credit,
or payment
instruments associated with the repayment transaction, and data characterizing
a
repayment schedule for the corresponding one of the financial, credit, or
payment
instruments, such as, but not limited to, an expected repayment data or an
expected
repayment amount, e.g., a minimum payment, etc.
[039] In one instance, all or a portion of the data maintained within
transaction
database 134 may be generated by monitoring system 130 (e.g., through
processes
that provision the commercial banking or other financial services to the one
or more
CA 3019195 2018-10-01
customers). In other instances, and consistent with the disclosed exemplary
embodiments, monitoring system 130 may receive all or a portion of the data
maintained within transaction database 134 from one or more external computing
systems through a corresponding programmatic interface, such as, but not
limited to, an
external computing system that stablishes or maintains a cloud-based storage
facility.
Further, the data records of transaction database 134 are not limited to the
exemplary
elements of transaction data described herein, and in other instances,
transaction
database 134 may include any additional or alternate elements of data
characterizing
exchanges of data between, or involving, the financial institution that
operates
monitoring system 130 or the customers of that financial institution, e.g.,
the commercial
or individual customers described herein.
[040] Referring back to FIG. 1, account database 135 may include data records
that identify and characterize one or more payment instruments, credit
instruments, or
other financial institutions provisioned to the customers of the financial
institution. For
example, and for the commercial customer described herein, the payment
instruments
may include, but are not limited to, a commercial credit card, and the credit
instruments
may include, but are not limited to, a revolving line-of-credit or a
commercial loan.
Further, and for each of the provisioned payment or credit instruments, the
data records
of account database 135 may include a unique identifier, such as a portion of
a
tokenized account number, data that identifies a current status, such as a
current
balance or an amount of principal, or data that establishes one or more terms
or
conditions, such as a repayment schedule or an interest rate.
[041] Further, monitoring database 136 may include one or more data records
that, when accessed and processed by monitoring system 130, facilitate or
support the
16
CA 3019195 2018-10-01
performance of any of the exemplary processes described herein. For example,
the
data records of monitoring database 136 may support the calculation of one or
more
metrics indicative of a financial risk to a financial institution that results
from the
provision of the commercial banking or other financial services to
corresponding
individual or commercial customers, e.g., based on an application of one or
more
statistical processes, machine learning processes, or artificial intelligence
processes to
portions of the data records maintained within customer database 132 and
transaction
databases 134. In other examples, the data records of monitoring database 136
may
include information that specifies and characterizes one or more segmentation
models
that, when implemented by monitoring system 130, facilitate a determination of
a risk
profile characterizing one or more of the individual or commercial customers,
and a
performance of additional operations consistent with the determined risk
profiles.
[042] Further, as illustrated in FIG. 1, monitoring system 130 may also
maintain,
within the one or more tangible, non-transitory memories, one or more
executable
application programs, such as a predictive engine 138. For example, when
executed by
monitoring system 130, predictive engine 138 may apply one or more predictive
models
to portions of the exemplary customer, transaction, and account data described
herein
(e.g., as maintained within customer database 132, transaction database 134,
and
account database 135). Based on the application of the one or more predictive
models,
executed predictive engine 138 may compute, for one or more of the customers
of the
financial institution (e.g., as identified within customer database 132), a
value of
composite metric that indicates a probability that a corresponding one of the
customers
performs an expected exchange of data in accordance with an expected parameter
value during a corresponding and future temporal interval. As described
herein, the
17
CA 3019195 2018-10-01
performance of the data exchange may, in some examples, facilitates a
servicing of one
or more existing obligations imposed on that corresponding customer by the
financial
institution (e.g., a scheduled payment on a revolving line of credit or a loan
provided to
the customer by the financial institution), and the computed value of
composite metric
may be indicative of a risk to the financial institution that results from the
provision of the
financial services to that corresponding customer.
[043] As described herein, executed predictive engine 138 may perform
operations that derive the value of composite metric for the each of the
customers of the
financial institution based on values of a plurality of component metrics. By
way of
example, for a commercial customer of the financial institution, the component
metrics
may characterize a risk to the financial institution that results from, among
other things,
a location, structure, or operations of the commercial customer (e.g., a
general metric),
a current or historical financial position or status of the commercial
customer (e.g., a
financial metric), or an interaction between the commercial customer and the
financial
institution during the provisioning of any of the exemplary financial services
described
herein (e.g., a behavioral metric).
[044] In some instances, predictive engine 138 may compute a value for the
general metric, the financial metric, and additionally, or alternatively,
based on an
application of one or more deterministic or stochastic statistical processes,
one or more
machine learning processes, or one or more artificial intelligence models to
portions of
the exemplary customer and transaction data described herein, e.g., as
maintained
within customer database 132, transaction database 134, and account database
135.
For example, the deterministic algorithms can include, but are not limited to,
a linear
18
CA 3019195 2018-10-01
regression model, a nonlinear regression model, a multivariable regression
model, and
additionally, or alternatively, a linear or nonlinear least-squares
approximation.
[045] Examples of the stochastic statistical processes can include, among
other
things, a support vector machine (SVM) model, a multiple regression algorithm,
a least
absolute selection shrinkage operator (LASSO) regression algorithm, or a
multinomial
logistic regression algorithm, and examples of the machine learning processes
can
include, but are not limited to, an association-rule algorithm (such as an
Apriori
algorithm, an Eclat algorithm, or an FP-growth algorithm) or a clustering
algorithm (such
as a hierarchical clustering process, a k-means algorithm, or other
statistical clustering
algorithms). Further, examples of the artificial intelligence models include,
but are not
limited to, an artificial neural network model, a recurrent neural network
model, a
Bayesian network model, or a Markov model. In some instances, these stochastic
statistical processes, machine learning algorithms, or artificial intelligence
models can
be trained against, and adaptively improved using, training data having a
specified
composition, which may be extracted from portions of customer database 132 and
transaction database 134 along with corresponding outcome data, and can be
deemed
successfully trained and ready for deployment when a model accuracy (e.g., as
established based on a comparison with the outcome data), exceeds a threshold
value.
[046] Further, and as described herein, executed predictive engine 138 may
also perform operations that determine the value for the composite metric for
each of
the customers of the financial institution based on combination of one or more
of the
component metric values, e.g., one or more of the general metric value, the
financial
metric value, and the behavioral metric value. For example, executed
predictive engine
138 may generate the composite metric value based on a linear combination of
the
19
CA 3019195 2018-10-01
general metric value, the financial metric value, and the behavioral metric
value (e.g., a
simple or a weighted average, etc.) or a nonlinear combination of the general
metric
value, the financial metric value, and the behavioral metric value (e.g., a
geometric
average, etc.). In other examples, executed predictive engine 138 may generate
the
composite metric value based on an application a regression model to one, or
more, of
the general metric value, the financial metric value, and the behavioral
metric value
(e.g., a multivariable regression model, etc.). The disclosed embodiments are,
however, not limited to these exemplary processes for computing the component
metric
values, or for computing the composite metric value based on all or a portion
of these
components values, and in other examples, executed predictive engine 138 may
compute the component metric values, or the composite metric value, using any
additional or alternate processes appropriate to the elements of input
customer or
transaction data, including those exemplary statistical processes, machine
learning
processes, or artificial intelligence models described herein.
[047] Executed predictive engine 138 may also perform operations that
parameterize a risk profile for each of the one or more customers based not
only on the
corresponding predicted value of the composite metric, but also on a derived
temporal
variation in each of the predicted values of the composite metric and
additionally, or
alternatively, on values of other parameters that characterize the customers,
the
financial services provided to the customers, or a relationship between the
customers
and the financial institution. In some instances, as described herein, the
parameterized
risk profile for a corresponding one of the customers, such as a commercial
customer of
the financial institution, can trigger an automatic performance, by monitoring
system 130
of one or more operations associated with the commercial customer or the
financial
CA 3019195 2018-10-01
services provided to that commercial customer. Examples of these triggered
operations
can include, but are not limited to, a generation and a delivery of a
programmatic
notification to one or more network-connected devices or systems operating
within
environment 100, such as client devices 102 or 122, or a dynamic review or
modification of the terms that characterize the provided financial services.
II. Exemplary Computer-Implemented Processes for Dynamically Monitoring
and Profiling Exchanges of Data within an Enterprise Environment
[048] In some exemplary embodiments, a network-connected computing
system, such as monitoring system 130 of FIG. 1, may access contextual data
that
identifies and characterizes one or more initiated or expected exchanges of
data
involving a first counterparty and one or more second counterparties. The
accessed
contextual data may, for instance, specify values of parameters that
characterize the
initiated or expected data exchanges, along with additional data
characterizing the first
counterparties and an interaction between the first counterparties and each of
the one
or more second counterparties. Further, and based on an application of one or
more
predictive models to selected portions of the accessed contextual data,
monitoring
system 130 may perform any of the exemplary processes described herein to
compute
a value of a metric that characterizes a likelihood that the first
counterparty will perform
one, or more, of the expected data exchanges in accordance with corresponding
one of
the parameter values (e.g., "expected" parameter values) during a future
temporal
interval.
[049] The computed metric value may, in some instances, represent a
composite metric value, which monitoring system 130 derives from a plurality
of
components values computed based an application of corresponding ones of the
predictive models to the selected portions of the accessed contextual data.
Further,
21
CA 3019195 2018-10-01
and as described herein, the one or more predictive models may include, among
other
things, a deterministic statistical process, a stochastic statistical process,
a machine
learning process, or an artificial intelligence model (or any combination
thereof), and
monitoring system 130 may perform operations that apply the one or more
predictive
models to the selected portions of the accessed contextual data, and that
compute the
metric value, at regular or predetermined intervals (e.g., daily, weekly,
monthly, etc.).
[050] In some instances, monitoring system 130 may obtain monitoring data that
specifies or identifies at least one triggering criterion associated with the
one or more
expected data exchanges, e.g., as maintained within monitoring database 136 of
FIG. 1.
As described herein, monitoring system 130 may perform operations that
establish a
consistency between the at least one triggering criterion and the computed
metric value,
taken individually or in combination with (i) a determined temporal evolution
in the
computed metric value over one or more prior temporal intervals and (ii) a
portion of the
accessed contextual data that characterizes an interaction between the first
and second
counterparties (e.g., "interaction" data).
[051] Based on the established consistency, monitoring system 130 may
perform further operations that include, but are not limited to, dynamically
modifying at
one or more of the expected parameter values that characterize the expected
data
exchanges, or generating and transmitting a signal that includes the computed
metric
value (and additionally, or alternatively, the temporal evolution of the
computed metric
value or the interaction data) to a device operated by at least one of the
first or second
counterparties. As described herein, the generated and transmitted signal may
include
information that causes an application program executed by the device (e.g.,
banking
application 108 or monitoring application 110 of FIG. 1) to present a
representation of
22
CA 3019195 2018-10-01
the computed metric value, the temporal evolution of the computed metric
value, and
additionally, or alternatively, the interaction data, within a corresponding
digital interface.
[052] In one example, and as described herein, monitoring system 130 can be
associated with, or operated by, a financial institution that provides
financial services of
one or more individual or commercial customers. For instance, the first
counterparty
may correspond to a commercial customer of the financial institution, which
can provide
commercial financial services that include, but are not limited to, issuing
and
maintaining deposit accounts (e.g., commercial checking accounts), issuing
commercial
credit cards or revolving lines of credit, providing transactions services
(e.g., payment
processing), or underwriting, holding, or services commercial loans. Further,
in some
instances, the initiated or expected exchanges of data (e.g., that involve the
first
counterparty) can facilitate a provisioning by the financial institution of
one or more of
these commercial financial services to the commercial customer, and the
servicing of
these provisioned financial serviced by the commercial customer, in accordance
with
certain parameter values, e.g., terms of the provisioned financial services.
[053] As described herein, the terms that characterize the provisioned
financial
services, and a risk to the financial institution that results from the
provision of these
financial services, can depend not only on an initial credit worthiness of the
commercial
customer (e.g., at an issuance of a credit card, revolving line of credit,
commercial loan,
etc.), but also on a subsequent behavior of and additional actions taken by
the
commercial customer. In some instances, the accessed contextual data can
identify
and characterize not only the commercial customer, the provisioned financial
services,
and the terms that characterize the provisioned financial services, but also
the
subsequent behavior of and the additional actions taken by the commercial
customer,
23
CA 3019195 2018-10-01
and the dynamically computed metric value may be indicative of an ongoing
risk, to the
financial institution that provisions the financial services to the commercial
customer,
that results from the subsequent behavior of and additional actions taken by
each of the
one or more customers.
[054] Monitoring system 130 may also perform operations that parameterize a
risk profile for the commercial customer based not only on the computed metric
value,
but also on a derived temporal variation in the computed metric value and
additionally,
or alternatively, on portions of the accessed contextual data that
characterize the
commercial customer, the financial services provisioned to the commercial to
the
customers, or a relationship between the commercial customer and the financial
institution (e.g., the second counterparty described herein). In some
instances, when
consistent with at least one triggering criterion, the parameterized risk
profile for the
commercial customer can trigger an automatic performance, by monitoring system
130
of one or more operations associated with the commercial customer or the
financial
services provided to that commercial customer, such as, but not limited to, a
generation
and a delivery of a programmatic notification to one or more network-connected
devices
or systems operating within environment 100, such as client devices 102 or
122, or a
dynamic review or modification of the terms that characterize the provided
financial
services.
[055] Using any of the exemplary processes described herein, monitoring
system 130 can dynamically and adaptively monitor a risk to a financial
institution that
results from a provisioning of certain services to a customer, can
parameterize a risk
profile for that customer based not only on a dynamically predicted value of a
metric
indicative of that risk, but also on a temporal evolution of that predicted
metric value
24
CA 3019195 2018-10-01
across one or more prior temporal intervals, and further, can dynamically
trigger a -
performance of certain operations based on a detected consistency between the
parameterized risk profile and at least one triggering criterion associated
with the
financial institution or the provisioned financial services. Certain of these
exemplary,
exception-based monitoring processes can be implemented in addition to, or as
an
alternate to, conventional processes that monitor risk for customers on a
continuous
basis during corresponding review periods and perform operations in response
to the
monitored risk upon conclusion of these review periods.
[056] Certain of these exemplary, exception-based monitoring processes may
also improve a speed and an efficiency at which monitoring system 130 monitors
and
acts upon the risk associated with the provision of financial services to
customers, as
these exception-based processes dynamically and selectively trigger the
performance
of operations based on the detected consistency between the at least one
triggering
criterion and the parameterized risk profiles of these customers, and not
automatically
for each monitored customer at a conclusion of the fixed and predetermined
review
period. Further, by applying one or more stochastic statistical processes,
machine
learning processes, or artificial intelligence models to portions of the
accessed
contextual data, certain of these exemplary exception-based monitoring
processes can
leverage and dynamically process elements of contextual data maintained in
cloud-
based storage or distributed data lakes in a manner not possible using
conventional or
human-implemented assessment processes.
[057] Referring to FIG. 2, an initiation module 202 of monitoring system 130
may perform operations that identify one or more customers of a financial
institution or
other business entity associated with monitoring system 130, such as, but not
limited to,
CA 3019195 2018-10-01
the individual or commercial customers of the financial institution described
herein. In
some instances, each of the customers may be associated with, and uniquely
identified
by, a corresponding customer identifier, and examples of these customer
identifiers
include, but are not limited to, an alphanumeric login name assigned to an
individual
customer or to an employee, representative, or other agent of a commercial
customer
(e.g., that facilitates a secure access to banking application 108), a device
identifier
associated with a network-connected device operated by an individual customer
or by
an employee, representative, or other agent of a commercial customer, or an
alphanumeric identifier assigned to one or more of the commercial customers.
Further,
initiation module 202 may identify the one or more customers, and may initiate
the
performance of the exemplary, exception-based monitoring processes described
herein,
at regular or predetermined intervals (e.g., daily, weekly, monthly, etc.) or
in response to
a detected occurrence of certain events, such as, but not limited to, a
detected breach
by a malicious third party or a request received from an external computing
system
operated by a regulator or a governmental entity.
[058] By way of example, and as illustrated in FIG. 2, initiation module 202
may
access data records maintained within customer database 132, and extract
identification data 204 associated with each of the customers of the financial
institution
or alternatively, associated with a subset of the customers of the financial
institution that
are subject to monitoring using any of the exemplary, exception-based
monitoring
processes described herein, e.g., one or more of the commercial customers of
the
financial institution.
[059] In some instances, identification data 204 may include one or more of
the
customer identifiers associated with assigned to all, or a portion, of the
customers of the
26
CA 3019195 2018-10-01
financial institution (e.g., the alphanumeric customer identifier, the
alphanumeric login
name, the device identifier, etc.). Further, and as described herein, the one
or more
customer identifiers may also be linked to additional elements of customer-
specific
profile data maintained within customer database 132, to elements of customer-
specific
transaction data maintained within transaction database 134 (e.g., which
identify and
characterize one or more exchanges of data initiated by, or on behalf of,
corresponding
ones of the customers during prior temporal intervals), and to elements of
customer-
specific account data maintained within account database 135 (e.g., which
identify and
characterize financial services provisioned to the customers). The disclosed
embodiments are, however, not limited to these exemplary elements of
identification
data 204, and in other instances, identification data 204 may include any
additional or
alternate data that identifies or characterizes all, or a subset, of the
customers of the
financial institution, such as, but not limited to, data characterizing a
parameterized risk
profile for one or more of the customers, e.g., as generated by monitoring
system 130
during a prior temporal interval.
[060] As illustrated in FIG. 2, initiation module 202 may provide
identification
data 204 as an input to predictive engine 138 of monitoring system 130, which
may
perform operations that compute, for each of the identified customers, a value
of metric
indicative of a likelihood that the customer performs an expected exchange of
data in
accordance with an expected parameter value during a corresponding and future
temporal interval. As described herein, the performance of the expected data
exchange
may, in some examples, facilitate a servicing of one or more existing
obligations
imposed on a corresponding one of the customers by the financial institution
(e.g., a
scheduled payment on a revolving line of credit or a loan provided to the
customer by
27
CA 3019195 2018-10-01
the financial institution), and the metric value computed for each of the
customers may
be indicative of a risk to the financial institution that results from the
provision of the
financial services to the each of the customers.
[061] As illustrated in FIG. 2, predictive engine 138 may include an input
processing module 206 that receives identification data 204, and parses
identification
data 204 to obtain each of the customer identifiers. In some instances, input
processing
module 206 may access customer database 132, transaction database 134, and
account database 135, and extract portions of the maintained customer,
transaction,
and account data that are linked to, and associated with, each of the obtained
customer
identifiers included within identification data 204.
[062] By way of example, input processing module 206 may extract, from the
data records of customer database 132, one or more elements of customer
profile data
208 that are associated with, or linked to, each of the customer identifiers
obtained from
identification data 204 and as such, that characterize a corresponding one of
the
individual or commercial customers of the financial institution. For instance,
one of the
obtained customer identifiers may be associated with a commercial customer of
the
financial institution, and the one of more extracted elements of customer
profile data
208 may include information that identifies a current or historical
organizational structure
of the commercial customer (e.g., an incorporated entity, a limited-liability
partnership,
etc.) and a jurisdiction in which the commercial customer is incorporated or
registered.
[063] Further, and for the commercial customer, the one of more extracted
elements of customer profile data 208 may also identify and characterize an
industry
within which the commercial customer operates, e.g., as specified by a four-
digit,
standard industrial classification (SIC) code, and additionally, or
alternatively, a financial
28
CA 3019195 2018-10-01
position of the commercial customer. For instance, and for the commercial
customer,
the extracted elements of customer profile data 208 may include, among other
things,
data characterizing earnings, assets, liabilities, or net (or gross) sales of
the particular
commercial customers across one or more reporting periods (e.g., based on
quarterly
reports, yearly reports, or tax returns generated for submission to one or
more
governmental or regulatory entities). Additionally, in some instances, the
extracted
elements of customer profile data 208 may also include information that
identifiers one
or more employees, representatives, or agents of the commercial customers,
such as,
but not limited to, the alphanumeric login name of user 101 or the unique
device
identifier of client device 102.
[064] In other examples, illustrated in FIG. 2, input processing module 206
may
extract, from the data records of transaction database 134, one or more
elements of
customer transaction data 210 that are associated with, or linked to, each of
the
customer identifiers obtained from identification data 204 and as such, that
are
associated with corresponding ones of the individual or commercial customers
of the
financial institution. In some instances, and for the commercial customer of
the financial
institution described herein, the one or more extracted elements of customer
transaction
data 210 may identify and characterize one or more exchanges of data initiated
by, or
on behalf of, that commercial customer during prior one or more temporal
intervals.
Further, the one or more extracted elements of customer transaction data 210
may
include, for each of the initiated data exchanges involving the commercial
customer, a
unique identifier of the initiated data exchange, data that identifies the
initiating user,
device, or customer (e.g., the commercial customer), an initiation time or
date, and
29
CA 3019195 2018-10-01
values of one or more parameters that characterize the corresponding one of
the
initiated data exchanges.
[065] By way of example, one or more of the initiated exchanges of data may
correspond to a purchase transaction involving a payment instrument (e.g., a
credit card
account, a debit card account linked to an underlying deposit account, etc.)
issued to
the commercial customer by the financial institution. In some instances, the
extracted
elements of customer transaction data 210 may specify for the initiated
purchase
transaction, parameter values that include an identifier of the payment
instrument (e.g.,
a portion of a tokenized account number, etc.), a transaction amount, a
transaction date
or time, a counterparty identifier (e.g., a merchant name or identifier), and
data
indicative of a purchased product or service (e.g., a universal product code
(UPC), etc.).
[066] In other instances, one or more of the initiated exchanges of data may
facilitate an issuance of a revolving line of credit, a commercial loan, a
payment
instrument or other financial, credit, or payment instrument to the commercial
customer
by the financial institution. The extracted elements of customer transaction
data 210
may include, for each of the issued financial, credit, or payment instruments,
data that
identifies the financial, credit, or payment instrument, a time or date of
issuance, and a
value of one or more parameters that characterize the financial, credit, or
payment
instrument, such as, but not limited to, an amount of available credit or a
corresponding
repayment schedule.
[067] One or more of the initiated data exchanges may also correspond to a
transaction initiated by the commercial customer in furtherance of a repayment
schedule associated with any of the financial, credit, or payment instruments
described
herein. In some instances, the extracted elements of customer transaction data
210
CA 3019195 2018-10-01
may include, for each of these repayment transactions, a corresponding
transaction
identifier, a transaction amount, a transaction data or time, an identifier of
the
corresponding one of the financial, credit, or payment instruments associated
with the
repayment transaction, and data characterizing a repayment schedule for the
corresponding one of the financial, credit, or payment instruments, such as,
but not
limited to, an expected repayment data or an expected repayment amount, e.g.,
a
minimum payment, etc.
[068] Further, and as illustrated in FIG. 2, input processing module 206 may
also extract, from the data records of account database 135, one or more
elements of
customer account data 212 that are associated with, or linked to, each of the
customer
identifiers obtained from identification data 204. In some instances, the
extracted
elements of customer account data 212 may identify and characterize one or
more
payment instruments (e.g., a credit card, etc.), credit instruments (e.g., a
revolving line
of credit, a commercial loan, etc.), or other financial instruments (e.g.,
deposit accounts,
etc.) issued by the financial institution to each of the customers associated
with the
obtained customer identifiers.
[069] For example, the extracted elements of customer account data 212 may
include data identifying each of the payment, credit, or financial instruments
(e.g., a
tokenized account number, etc.), along with additional status data
characterizing each
customer's current or prior use or interaction with the payment, credit, or
financial
instruments. The additional status data may identify, for each of the payment,
credit, or
financial instruments, a current and historical balance of available funds
(e.g., a balance
history), fees incurred by through the use of the payment, credit, or
financial instruments
(e.g., an amount and assessment date of expected fees, overdraft fees,
negative-
31
CA 3019195 2018-10-01
balance fees, etc.), a time or date of any overdraft (e.g., for a deposit
account) or a
negative balance (e.g., a revolving line of credit), and a time or date of any
delinquencies (e.g., exceeding an available balance, a late or insufficient
payment, etc.).
[070] The disclosed embodiments are, however, not limited to these examples
of customer-specific profile, transaction, or account data. In other
instances, the
extracted elements of customer profile data 208, customer transaction data
210, and
customer account data 212 may include any additional, or alternate,
information that
characterizes the commercial customer described herein and the interaction of
that
commercial customer with the financial institution or with payment, credit, of
financial
instruments issued by that financial institution. Further, the disclosed
embodiments are
also not limited to elements of customer profile, transaction, or account data
that
characterize commercial customers of the financial institution, and in some
instances,
the extracted elements of customer profile data 208, customer transaction data
210,
and customer account data 212 may also identify and characterize one or more
individual customers of the financial institution (e.g., users 101 or 121 of
FIG. 1), and an
interaction of the one or more individual customers with the financial
institution or with
payment, credit, or financial instruments.
[071] Based on the extracted elements of customer profile data 208, customer
transaction data 210, and customer account data 212, input processing module
206
may generate discrete elements of input data 214 for provisioning to
corresponding
ones of a plurality of predictive modules 216 of predictive engine 138. In
some
instances, predictive modules 216 may apply one or more predictive models to
the
discrete elements of input data 214, and based on the application of these one
or more
predictive models, predictive modules 216 may perform operations that predict
a
32
CA 3019195 2018-10-01
corresponding one of a plurality of component metric values 218 for each of
the
customers of the financial institution identified within the discrete elements
of input data
214. As described herein, an aggregated risk to the financial institution
resulting from
the provisioning of financial services to the each of these customers (e.g.,
as specified
within identification data 204 and as identified within input data 214) may
depend on
multiple, customer-specific risk factors, and each of predicted component
metric values
218 may characterize a portion of the aggregated risk that results from
corresponding
ones of these customer-specific risk factors.
[072] For example, and as described herein, the extracted elements of customer
profile data 208, customer transaction data 210, and customer account data 212
may
be associated with one or more commercial customers of the financial
institution (and
may be associated with, or include, corresponding customer identifiers). In
some
instances, the aggregated risk to the financial institution due to the
provisioning of
commercial financial services to these commercial customers may depend on risk
factors that include, but are not limited to: (i) a location, structure, or
operations of each
of the commercial customers (e.g., a general risk factor); a current or
historical financial
position or status of each of the commercial customers (e.g., a financial risk
factor); and
an interaction between each of the commercial customers and the financial
institution
during the provisioning of any of the exemplary commercial financial services
described
herein (e.g., a behavioral risk factor). As illustrated in FIG. 2, and to
facilitate a
prediction of the plurality of component metric values 218 that characterize
respective
ones of the general, financial, and behavioral risk factors, predictive
modules 216 may
include, but are not limited to, a general predictive module 216A that
predicts a general
metric value 218A characterizing the general risk factor for each of the
customers, a
33
CA 3019195 2018-10-01
financial predictive module 216B that predicts a financial metric value 218B
characterizing the financial risk factor for each of the customers, and a
behavioral
predictive module 216C that predicts a behavioral metric value 218C
characterizing the
behavioral risk factor for each of the customers.
[073] In some instances, as illustrated in FIG. 2, general predictive module
216A, financial predictive module 216B, and behavioral predictive module 216C
may
apply one or more predictive models to corresponding ones of model-specific
input data
214A, 214B, and 214C (e.g., that collective establish input data 214). Based
on the
application of these predictive models, general predictive module 216A,
financial
predictive module 216B, and behavioral predictive module 216C may predict
corresponding ones of general metric value 218A, financial metric value 218B,
behavioral metric value 218C for each of the customer identifiers included
within
identification data 204.
[074] As described herein, the one or more predictive models applied by each
of
general predictive module 216A, financial predictive module 216B, and
behavioral
predictive module 216C may include, but are not limited to, a deterministic
statistical
process, a stochastic statistical process, a machine learning process, or an
artificial
intelligence model. For example, the deterministic statistical processes can
include, but
are not limited to, an index based on certain parameter values, a linear
regression
model, a nonlinear regression model, a multivariable regression model, and
additionally,
or alternatively, a linear or nonlinear least-squares approximation. Examples
of the
stochastic statistical process can include, among other things, a support
vector machine
(SVM) model, a multiple regression algorithm, a least absolute selection
shrinkage
operator (LASSO) regression algorithm, or a multinomial logistic regression
algorithm,
34
CA 3019195 2018-10-01
and examples of the machine learning processes can include, but are not
limited to, an
association-rule algorithm (such as an Apriori algorithm, an Eclat algorithm,
or an FP-
growth algorithm) or a clustering algorithm (such as a hierarchical clustering
process, a
k-means algorithm, or other statistical clustering algorithms). Further,
examples of the
artificial intelligence model include, but are not limited to, an artificial
neural network
model, a recurrent neural network model, a Bayesian network model, or a Markov
model.
[075] As illustrated in FIG. 2, input processing module 206 may access
monitoring database 136, and may extract a first portion of modelling data 220
that
specifies the one or more predictive models applied by general predictive
module 216A
to predict general metric value 218A, and that also specifies certain elements
of input
data associated with the one or more predictive models (e.g., parameter values
extracted or derived from customer profile data 208, customer transaction data
210, and
customer account data 212). By way of example, and without limitation, the
first portion
of modelling data 220 may specify that general metric value 218A represents a
general
index value computed based on elements of input data that include, but are not
limited
to, a jurisdiction in which a commercial customer operated or is incorporated,
a standard
industrial classification (SIC) code assigned to the commercial customer, or a
duration
of a relationship between the commercial customer and the financial
institution. The
accessed first portion of modelling data 220 may also include information that
facilitates
a prediction of general metric value 218A based on the customer-specific,
general input
data, e.g., information specifying a linear, non-linear, or geometric
combination of the
elements of general input data and a corresponding normalization scheme.
CA 3019195 2018-10-01
[076] In some instances, input processing module 206 may perform operations
that parse the first portion of modelling data 220 to identify those elements
of general
input data associated with general predictive module 216A (e.g., the
jurisdictional data,
the SIC code, and the relationship duration), and may obtain the identified
elements of
general input data from customer profile data 208 (e.g., and additionally, or
alternatively,
from portions of customer transaction data 210 or customer account data 212).
Input
processing module 206 may package the obtained elements of general input data
and
corresponding customer identifiers into portions of input data 214A, which
input
processing module 206 may provide as an input to general predictive module
216A. In
some examples, general predictive module 216A may process portions of input
data
214A in accordance with the first portion of modelling data 220, and may
compute the
general index value associated with each of the customers specified within
input data
214A (e.g., as associated with corresponding customer identifiers). General
predictive
module 216A may associate each of the general index values with a
corresponding one
of the customer identifiers, and package the general index values and the
associated
customer identifiers within general metric values 218A (e.g., which
establishes an array
of associated general index values and customer identifiers).
[077] Further, input processing module 206 may also extract, from monitoring
database 136, a second portion of modelling data 220 that specifies the one or
more
predictive models applied by financial predictive module 216B to predict
financial metric
values 218B, and that also specifies certain elements of input data (e.g.,
"financial input
data") associated with the one or more predictive models. By way of example,
and
without limitation, the second portion of modelling data 220 may specify that
financial
metric value 218B represents a financial index value computed based on
elements of
36
CA 3019195 2018-10-01
financial input data that include, but are not limited to, current or
historical sales data for
a commercial customer (e.g., sales volume, an aggregate value, a growth in a
value of
volume of sales over multiple temporal intervals, etc.), data characterizing
assets held
by the commercial customer (e.g., types of assets, values of the assets,
etc.), or data
characterizing liabilities of the commercial customer (e.g., types of
liabilities, aggregate
value of the liabilities, terms associated with these liabilities, etc.). As
described herein,
the accessed second portion of modelling data 220 may also include information
that
facilitates a prediction of financial metric values 218B based on the
specified input data,
e.g., information specifying a linear, non-linear, or geometric combination of
the
specified elements of input data and a corresponding normalization scheme.
[078] Input processing module 206 may perform operations that parse the
second portion of modelling data 220 to identify those elements of financial
input data
associated with financial predictive module 216B (e.g., the sales, asset,
and/or liability
data). In some instances, input processing module 206 may obtain at least a
portion of
the specified elements of financial input data from customer profile data 208
(e.g., and
additionally, or alternatively, from portions of customer transaction data 210
or customer
account data 212). Further, input processing module 206 may also derive
additional
portions of the financial input data, e.g., the temporal evolution in a
commercial
customer's sales, from portions of those elements of input data obtained from
customer
profile data 208, customer transaction data 210, or customer account data 212
[079] Input processing module 206 may package the obtained or derived
elements of financial input data and corresponding customer identifiers into
portions of
input data 214B, which input processing module 206 may provide as an input to
financial predictive module 216B. In some examples, financial predictive
module 216B
37
CA 3019195 2018-10-01
may process portions of input data 214B in accordance with the second portion
of
modelling data 220, and may compute the financial index value associated with
each of
the customers specified within input data 214B (e.g., as associated with
corresponding
customer identifiers). Financial predictive module 216B may associate each of
the
financial index values with a corresponding one of the customer identifiers,
and package
the general index values and the associated customer identifiers within
financial metric
values 218B (e.g., which establishes an array of associated financial index
values and
customer identifiers).
[080] In other examples, input processing module 206 may extract, from
monitoring database 136, a third portion of modelling data 220 that specifies
the one or
more predictive models applied by behavioral predictive module 216C to predict
behavioral metric values 218C, and that also specifies certain elements of
input data
associated with the one or more predictive models. By way of example, and
without
limitation, the third portion of modelling data 220 may specify that
behavioral metric
values 218B represent a financial index values computed based on elements of
input
data that, among other things, characterize an interaction between each of the
customers and not only the financial institution, but also the payment,
credit, or other
financial instruments issued or serviced by that financial institution.
[081] For instance, the elements of input data associated with behavioral
predictive module 216C may include, but are not limited to: (i) data
characterizing one
or more occurrences of a overdrafts involving the financial instruments issued
to the
customers, e.g., a number of overdrafts within a specified period, a temporal
interval
between overdrafts, a value of one or more of the overdrafts, etc.; (ii) data
characterizing balances, including negative balances, of one or more of the
payment,
38
CA 3019195 2018-10-01
credit, or financial instruments issued by the customers, e.g., actual
balances,
occurrences of negative balances, durations of negative and positive balances,
a
temporal interval between negative balances, etc.; and (iii) data
characterizing fees paid
by the customers due to overdrafts, negative balances, or other delinquency
events,
e.g., aggregate amounts of fees paid due to overdrafts, negative balances, or
other
delinquency events during one or more temporal intervals, a temporal
evolutions in the
fees paid, etc. Further, and as described herein, the accessed third portion
of modelling
data 220 may also include information that facilitates a prediction of
behavioral metric
values 218B based on the specified input data, e.g., information specifying a
linear,
non-linear, or geometric combination of the specified elements of input data
and a
corresponding normalization scheme for the behavioral index values.
[082] Input processing module 206 may perform operations that parse the third
portion of modelling data 220 to identify those elements of input data
associated with
behavioral predictive module 216C. In some instances, input processing module
206
may obtain at least a portion of the specified elements of the behavioral
input data from
customer profile data 208 (e.g., and additionally, or alternatively, from
portions of
customer transaction data 210 or customer account data 212). Further, input
processing module 206 may also derive additional portions of the specified
input data,
e.g., the temporal evolution in a commercial customer's sales, from portions
of those
elements of input data obtained from customer profile data 208, customer
transaction
data 210, or customer account data 212.
[083] As described herein, input processing module 206 may package the
obtained or derived elements of behavioral input data and corresponding
customer
identifiers into portions of input data 214C, which input processing module
206 may
39
CA 3019195 2018-10-01
provide as an input to behavioral predictive module 216C. In some examples,
behavioral predictive module 216C may process portions of input data 214C in
accordance with the third portion of modelling data 220, and may compute the
financial
index value associated with each of the customers specified within input data
214C
(e.g., as associated with corresponding customer identifiers). Behavioral
predictive
module 216C may associate each of the financial index values with a
corresponding
one of the customer identifiers, and package the behavioral index values and
the
associated customer identifiers within behavioral metric values 218C (e.g.,
which
establishes an array of associated behavioral index values and customer
identifiers).
[084] Referring back to FIG. 2, predictive modules 216 may provide component
metric values 218, which include, but are not limited to, general metric
values 218A,
financial metric values 218B, and behavioral metric values 218C, as an input
to an
aggregation module 222 of predictive engine 138. In some instances,
aggregation
module 222 may perform any of the exemplary processes described herein to
compute,
for each of the identified customers, a composite metric value 224 based on
combinations of corresponding ones of general metric values 218A, financial
metric
values 218B, and behavioral metric values 218C. Each of composite metric
values 224
may, for example, reflect a risk to the financial institution that results
from a provisioning
of financial services to corresponding ones of the customers (e.g., the
commercial
customers described herein), and may represent a relative contribution of the
generate,
financial, and behavioral risk factors described herein,
[085] In some examples, aggregation module 222 may generate, for each of the
identified customers, a corresponding one of composite metric values 224 based
on a
linear combination of corresponding ones of general metric values 218A,
financial
CA 3019195 2018-10-01
metric values 218B, and behavioral metric values 218C (e.g., a simple or a
weighted
average, etc.) or based on a non-linear combination of corresponding ones of
general
metric values 218A, financial metric values 218B, and behavioral metric values
218C
(e.g., a geometric average, a non-linear or polynomial function, etc.). In
other
examples, aggregation module 222 may generate a corresponding one of composite
metric values 224 for each of the identified customers based on an application
a
regression model to corresponding ones of general metric values 218A,
financial metric
values 218B, or behavioral metric values 218C (e.g., a multivariable
regression model,
a multiple linear or non-linear regression model, a logistic repression model,
etc.).
[086] Additionally, in some examples, component metric values 218 may
establish a multidimensional metric-value coordinate space, and one or more
composite
metric values 224 may be represented a vector within that multidimensional
metric-
value coordinate space having components defined by corresponding ones of
component metric values 218. For instance, component metric values 218 may
include
general metric values 218A, financial metric values 218B, or behavioral metric
values
218C ranging in magnitude from zero (e.g., no risk) to unity (e.g., highest
risk), and as
illustrated in FIG. 3A, a multidimensional metric-value coordinate space 302
may be
defined by coordinate axes associated with respective ones of the general
metric (e.g.,
coordinate axis 304 of FIG. 3A), the financial metric (e.g., coordinate axis
306 of FIG.
3A), and the behavior metric (coordinate axis 308 of FIG. 3A).
[087] Further, and for each of the identified customers (e.g., the commercial
customers described herein), corresponding ones of the general metric values
218A,
financial metric values 218B, or behavioral metric values 218C can establish a
triplet of
component values that establishes a vector within the multidimensional metric-
value
41
CA 3019195 2018-10-01
coordinate space, e.g., multidimensional metric-value coordinate space 302 of
FIG. 3A.
In some instances, aggregation module 222 may compute the composite metric
value
for each of the customers (e.g., corresponding ones of composite metric values
224)
based a determined magnitude of the corresponding vector within
multidimensional
metric-value coordinate space, such as, but not limited to, a Euclidean norm
of the
corresponding vector or a quadratic form of the corresponding vector.
[088] As illustrated in FIG. 3A, and for a particular one of the commercial
customers, the corresponding ones of general metric values 218A, financial
metric
values 218B, or behavioral metric values 218C can establish a Euclidean
vector, e.g.
vector 310, within multidimensional metric-value coordinate space 302.
Further, also
illustrated in FIG. 3A, scalar projection 312 of vector 310 onto coordinate
axis 304
represents the corresponding one of general metric values 218A associated with
the
particular commercial customer, a scalar projection 314 of vector 310 onto
coordinate
axis 306 represents the corresponding one of financial metric values 218B
associated
with the particular commercial customer, and a scalar projection 316 of vector
310 onto
coordinate axis 308 represents the corresponding one of behavioral metric
values 218C
associated with the particular commercial customer. Further, and as described
herein,
aggregation module 222 may establish a determine magnitude of vector 310
(e.g., as a
Euclidean norm of scalar projections 312, 314, and 316) as a composite metric
value for
the particular commercial customer.
[089] The disclosed embodiments are, however, not limited to these exemplary
processes for computing composite metric values for the identified customers
based on
corresponding elements of general metric values 218A, financial metric values
218B, or
behavioral metric values 218C. In other instances, aggregation module 222 can
42
CA 3019195 2018-10-01
perform any additional, or alternate, operations that combine or aggregate the
elements
of general metric values 218A, financial metric values 218B, or behavioral
metric values
218C, or any other appropriate one of component metric values 218, into
corresponding
elements of composite metric values 224 for the commercial customers of the
financial
institution, for one or more individual customers of the financial
institution, or for any
combination thereof.
[090] Referring back to FIG. 2, aggregation module 222 may associate the
determined composite metric values for each of the identified customers with a
corresponding one of the customer identifiers, and may package the composite
metric
values and the associated customer identifiers within corresponding elements
of
composite metric values 224. In some instances, aggregation module 222 may
provide
all or a portion of composite metric values 224 (e.g., that specify the
component metric
values for each of the identified customers of the financial institution, such
as the
commercial customers described herein) as an input to a risk parameterization
module
226 of predictive engine 138. In some instances, risk parameterization module
226 may
perform operations that parameterize a multidimensional risk profile, and
generate a
corresponding element of risk profile data 228, for each of the identified
customers
based on corresponding ones of composite metric values 224, a time evolution
of the
corresponding one of composite metric value 224 across one or more prior
temporal
intervals, and additional data characterizes an interaction between the
identified
customers and the financial institution.
[091] By way of example, risk parameterization module 226 may extract a
composite metric value for each of the identified customers (e.g., the
commercial
customer described herein) from composite metric values 224. Risk
parameterization
43
CA 3019195 2018-10-01
module 226 may also access the data records of monitoring database 136 and
extract
metric value data 230 that specifies, for one or more of the identified
customers, the
composite metric values determined during at least one prior temporal
interval. Further,
and as illustrated in FIG. 2, risk parameterization module 226 may access one
or more
of customer profile data 208, customer transaction data 210, or customer
account data
212 and extract all or a portion of the additional data characterizes an
interaction
between the identified customers and the financial institution. For instance,
risk
parameterization module 226 may access customer transaction data 210 and
extract
exposure data 232 characterizing an amount of credit associated with one or
more
payment instruments (e.g., a credit card), credit instruments (e.g., a
revolving line of
credit or a commercial loan), or other financial instruments issued by the
financial
institution to each of the identified customers, e.g., the commercial
customers described
herein.
[092] Based on metric value data 230, risk parameterization module 226 may
perform operations that compute a temporal evolution 234 in the composite
metric score
(e.g., as specified within composite metric values 224) for each of the
identified
customers. In some instances, however, metric value data 230 may fail to
specify a
previously determined composite metric value for one or more of the identified
customers (e.g., a current monitoring cycle may represent a first application
of the
exemplary, exception-based monitoring processes to these one or more
identified
customers), and based on the lack of the previously determined metric value,
risk
parameterization module 226 may assign predetermined value to temporal
evolution
234 for these one or more identified customers, such as a value or zero, a
value or
unity, or an alphanumeric flag. Further, and based on exposure data 232, risk
44
CA 3019195 2018-10-01
parameterization module 226 may compute, for each of the identified customers,
a
value 236 indicative of a total exposure of the financial institution (e.g., a
total amount of
extended credit) that results from the issued payment, credit, or other
financial
instruments.
[093] Referring back to FIG. 2, risk parameterization module 226 may generate
an element of risk profile data 228 for each of the identified customers that
includes, but
is not limited to a corresponding one of the customer identifiers, a
corresponding one of
composite metric values 224, a corresponding one of computed temporal
evolutions
234, and a corresponding one of the total exposure values 236. In some
instances, by
establishing the multidimensional risk profile for a particular customer based
on the
composite metric value and the temporal evolution of that composite metric
value,
certain of the exemplary, exception-based monitoring processes can
characterize the
risk to the financial institution derived from not only the general,
financial, or behavioral
characteristics of the particular customer, but also on a detected volatility
in these
characteristics (e.g., a customer characterized by a small, but highly
volatile, composite
metric value may represent more substantial risk to the financial institution
than an
additional customer characterized by a larger, but stable, composite metric
value).
[094] Further, by establishing the multidimensional risk profile for the
particular
customer based on the total exposure of the financial institution to payment,
credit, or
other financial instruments issued to that particular customer, certain of the
exemplary,
exception-based monitoring processes described herein can further characterize
the
risk to the risk to the financial institution derived from that exposure, even
when that
exposure results from otherwise stable, risk-averse customers. For example, a
customer characterized by relatively small and stable composite metric value,
but a
CA 3019195 2018-10-01
significant credit exposure, may represent a more significant risk to the
financial
institution than an additional customer characterized by a larger or more
volatile
composite metric value, but a minimal credit exposure.
[095] Referring back to FIG. 2, risk parameterization module 226 may provide
the elements of risk profile data 228, which establish and parameterize the
multidimensional risk profile for each of the customers, to a risk
segmentation module
238 of predictive engine 138. In some instances, and as described herein, risk
segmentation module 238 may access each element of risk profile data 228,
which
specifies a composite metric value (e.g., a corresponding one of composite
metric
values 224), a temporal evolution in that composite metric value (e.g., a
corresponding
one of temporal evolutions 234), and a value of a total exposure (e.g., a
corresponding
one of total exposure values 236) for a corresponding one of the identified
customers of
the financial institution. Based on corresponding ones of the composite metric
values,
the temporal evolutions, and the total exposure values (e.g., within the
accessed
elements of risk profile data 228), risk segmentation module 238 may perform
any of the
exemplary processes described herein segment the identified customers of the
financial
institution into corresponding levels of potential risk, e.g., low risk,
slight risk, strong risk,
or high risk.
[096] As illustrated in FIG. 2, risk segmentation module 238 may access the
data records of monitoring database 136 and extract segmentation data 240,
which
identifies and characterizes each of the levels of potential risk to the
financial institution,
and further, which facilitates a segmentation of each of the customers into a
corresponding one of the levels of potential risk. In some instances,
segmentation data
240 may define each of the levels of potential risk (e.g., low risk, slight
risk, strong risk,
46
CA 3019195 2018-10-01
or high risk) based on a corresponding value, or range of values, of the
composite
metric value, the temporal evolution in the composite metric value, and
additionally, or
alternatively, the total exposure value.
[097] In some examples, segmentation data 240 may define a first threshold
value associated with the composite metric value, a second threshold value
associated
with the temporal evolution in the composite metric value, and a third
threshold value
associated with the total exposure value. Further, segmentation data 240 may
segment
each of the identified customers into a corresponding one of the levels of
potential risk
based on a determined satisfaction of a first threshold criterion (e.g., that
the composite
metric value exceeds the first threshold value), a second threshold criterion
(e.g., that
the rate of change of the composite metric value exceeds the second threshold
value),
or a third threshold criterion (e.g., that the total exposure value exceeds a
third
threshold value).
[098] For instance, segmentation data 240 may specify that a particular one of
the identified customers represents a "low risk" to the financial institution
when a
corresponding element of risk profile data 228 satisfies neither the first,
second, nor
third threshold criteria. In other instances, segmentation data 240 may
specify that the
particular one of the identified customers represents a "slight risk" to the
financial
institution when the corresponding element of risk profile data 228 satisfies
a single one
of the first, second, or third threshold criteria, and additionally, or
alternative, that the
particular one of the identified customers represents a "strong risk" to the
financial
institution when the corresponding element of risk profile data 228 satisfies
any two of
the first, second, or third threshold criteria. Further, segmentation data 240
may also
specify that the particular one of the identified customers represents a "high
risk" to the
47
CA 3019195 2018-10-01
financial institution when the corresponding element of risk profile data 228
satisfies
each of the first, second, or third threshold criteria.
[099] In other examples, segmentation data 240 may also define ranges of the
composite metric value, the rate of change of that composite metric value, and
the total
exposure value that would characterize the provision of the financial services
to a
particular customer as a low risk, a slight risk, strong risk, or a high risk
to the financial
institution. By way of example, segmentation data 240 may define a low-risk
range for
each of the composite metric value, the rate of change in that composite
metric value,
and the total exposure value, and may further specify that a particular one of
the
identified customers represents a "low risk" to the financial institution when
its
corresponding composite metric value, rate of change, and total exposure value
are
each disposed within corresponding ones of the low-risk ranges of values.
Segmentation data 240 may also define a high-risk range for each of the
composite
metric value, the rate of change in that composite metric value, and the total
exposure
value, and may specify that a particular one of the identified customers
represents a
"high risk" to the financial institution when one, or more, of its composite
metric value,
rate of change, and total exposure value are disposed within a corresponding
one of the
high-risk ranges of values.
[0100] Further, segmentation data 240 may also define one or more ranges, or
combinations of ranges, of the composite metric value, the rate of change of
that
composite metric value, and the total exposure value that would characterize
the
provision of the financial services to a particular customer as a slight risk
or strong risk
to the financial institution. For instance, segmentation data 240 may specify
that a
particular one of the identified customers represents a slight risk to the
financial
48
CA 3019195 2018-10-01
institution when its composite metric value, rate of change, and total
exposure value are
each disposed within a corresponding one of the slight-risk ranges of values
and
additionally, or alternatively, when its composite metric value, rate of
change, and total
exposure value are each disposed within a specified combination of the
corresponding
ones of the low- and slight-risk ranges. For example, segmentation data 240
may
establish that the provision of the financial services to the particular
customer may be
considered a slight risk to the financial institution when the particular
customer's
composite metric value is disposed within a low-risk range, and when the rate
of change
in the particular customer's composite metric score and the particular
customer's total
exposure value are each disposed within a slight-risk range.
[0101] Segmentation data 240 may also specify that a particular one of the
identified customers represents a "strong risk" to the financial institution
when its
composite metric value, rate of change, and total exposure value are each
disposed
within a corresponding one of the strong-risk ranges of values and
additionally, or
alternatively, when its composite metric value, rate of change, and total
exposure value
are each disposed within a combination of the corresponding strong-risk
ranges, slight
risk ranges, and in some instances, low-risk range. For example, segmentation
data
240 may establish that the provision of financial services to a particular
customer may
be considered a strong risk to the financial institution when the particular
customer's
composite metric value and total exposure value are each disposed within a
strong risk
range, and when the rate of change in the particular customer's composite
metric value
is disposed within either of a low- or slight-risk range.
[0102] In other instances, and as illustrated in FIG. 3B, each element of risk
profile data 228 may also be represented as a Euclidean vector (e.g., a "risk"
vector) for
49
CA 3019195 2018-10-01
the corresponding customer within a multidimensional coordinate space, e.g., a
"risk"
space 320 parameterized by the composite metric values V, the temporal rates
of
change AV in the composite metric values, and the total exposure values E. For
example, in FIG. 3B, an initial point of a risk vector (e.g., -tic) for a
particular one of the
identified customers (e.g., customer C) may be disposed at an origin of risk
space, e.g.,
point {0, 0, 0} in risk space 320. Further, in FIG. 3B, a terminal point of
the risk vector
fic may be disposed at a point within the risk space defined by the particular
customer's
composite metric value Vc, the temporal rate change AV, in the particular
customer's
composite metric value, and total exposure value Ec (e.g., point {Vc, AK, Ec}
in risk
space 320 FIG. 3B).
[0103] In some examples, segmentation data 240 may decompose or segment
the risk space into discrete, bounded regions that include corresponding
points within
the risk space (e.g., as defined by corresponding composite metric values,
temporal
rates of change, and total exposure values), and assign a level of potential
risk to each
of the bounded subspaces. For instance, as illustrated in FIG. 3C,
segmentation data
240 may decompose risk space 320 into subspaces that include, but are not
limited to:
(i) a first subspace 332 associated with composite metric values, temporal
rates of
change, and total exposure values that represent a low risk to the financial
institution,
e.g., indicated by the dotted regions of risk space 320; (ii) a second
subspace 334
associated with composite metric values, temporal rates of change, and total
exposure
values that represent a slight risk to the financial institution, e.g.,
indicated by the
diagonally hashed regions of risk space 320; (iii) a third subspace 336
associated with
composite metric values, temporal rates of change, and total exposure values
that
represent a strong risk to the financial institution, e.g., indicated by the
crossed-hash
CA 3019195 2018-10-01
regions of risk space 320; and (iv) a fourth subspace 338 associated with
composite
metric values, temporal rates of change, and total exposure values that
represent a high
risk to the financial institution, e.g., the regions of risk space 320 without
dots or
hashing.
[0104] In some instances, risk segmentation module 238 may, for a particular
one of the identified customers, access a corresponding element of risk
profile data 228,
and extract the composite metric value, the temporal rate change in that
composite
metric value, and the total exposure value for that particular customer. As
illustrated in
FIG. 3D, the composite metric value (e.g., Vc), the temporal rate of change in
that
composite metric value (e.g., AK), and the total exposure value (e.g., Ec) may
establish
a risk vector fic for the particular customer within risk space 320. Further,
and as
illustrated in FIG. 3D, segmentation module 340 may perform any of the
exemplary
processes described herein to establish that a terminal point of that
corresponding risk
vector fic, e.g., point Vc, AK, Ec}, is disposed within fourth subspace 338 of
risk space
320, which indicates that the provision of the financial services to the
particular
customer represents a high risk to the financial institution.
[0105] As described herein, segmentation data 240 may, when processed by risk
segmentation module 238, facilitate a segmentation of the identified customers
into
corresponding levels of risk to the financial institution based on the
parameter-specific
threshold values, the risk-level-specific ranges of parameter values and
additionally, or
alternatively, the segmentation of the risk subspace into corresponding ones
of the risk-
level-specific subspaces. In some instances, one or more of these parameter-
specific
threshold values, risk-level-specific ranges of parameter values or risk-level-
specific
subspaces may be established, or empirically determined by the financial
institution
51
CA 3019195 2018-10-01
associated with monitoring system 130, e.g., based on predetermined risk-
management
protocols or based on requirements set forth by a governmental or regulatory
entity. In
other instances, monitoring system 130 may perform operations that adaptively
determine one or more parameter-specific threshold values, risk-level-specific
ranges of
parameter values or risk-level-specific subspaces based on an application of
any of the
machine learning processes or artificial intelligence models described herein
to training
data, e.g., the composite metric values, temporal rates of change in the
composite
metric values, and total exposure values, associated with known or observed
levels of
risk to the financial institution, e.g., low, slight, strong, or high risk.
[0106] Referring back to FIG. 2, and risk segmentation module 238 may access
the one or more elements of risk profile data 228 for each identified customer
of the
financial institution (e.g., as received as an input from risk
parameterization module 226)
and may obtain segmentation data 240 from the data records of monitoring
database
136. Based on the elements of risk profile data 228 and corresponding portions
of
segmentation data 240, risk segmentation module 238 may perform any of the
exemplary processes described herein to assign a corresponding one of the
levels of
potential risk to the financial institution, e.g., low risk, slight risk,
strong risk, or high risk,
to each of the identified customers of the financial institution.
[01071 In some instances, risk segmentation module 238 may generate risk level
data 242 that includes, for each of the identified customers of the financial
institution,
the corresponding customer identifier and the assigned risk level associated
with the
provision of financial services to that customer by the financial institution,
e.g., the low,
slight, strong, or high risks described herein. Risk segmentation module 238
may also
perform operations that store generated risk level data 242 within a locally
accessible
52
CA 3019195 2018-10-01
data repository, such as, but limited to, monitoring database 136, along with
temporal
data characterizing a time or date at which risk segmentation module 238
assigned the
levels of potential risk to the identified customers. Further, risk
segmentation module
238 may provide risk profile data 228 and risk level data 242 as inputs to an
exception
module 244 of monitoring system 130, which may perform any of the exemplary
processes described herein to identify, and trigger an initiation of, one or
more
operations consistent with the level of potential risk assigned to each of the
identified
customers of the financial institution (e.g., as specified within risk level
data 242) and
additionally, or alternatively, with the parameterized risk profile of each of
these
identified customers (e.g., as specified within risk profile data 228).
[0108] Referring to FIG. 4A, exception module 244 may receive risk profile
data
228, which parameterizes the risk profile for each of the identified customers
of the
financial institution, and risk level data 242, which identifies a level of
potential risk to
the financial institution resulting from the provisioning of financial
services to each of the
identified customers As described herein, risk profile data 228 may include,
for each of
the identified customer, a corresponding customer identifier 402 (e.g., an
alphanumeric
identifier, etc.), a composite metric value (e.g., a corresponding one of
composite metric
values 224), a temporal rate of change in that composite metric value (e.g., a
corresponding one of temporal evolutions 234), and a total exposure value
(e.g., a
corresponding one of the total exposure values 236). Further, and as described
herein,
risk level data 242 may include, for each of the identified customers,
corresponding
customer identifier 402 and an assigned level of potential risk 404, e.g., any
of the low,
slight, strong, and high levels of potential risk described herein.
53
CA 3019195 2018-10-01
[0109] Upon receipt of risk profile data 228 and risk level data 242,
exception
module 244 may perform operations that access the data records of monitoring
database 136, and that extract exception data 406 that, among other things,
identifies
and characterizes operations consistent with each of the levels of customer
risk, e.g.,
the low, slight, strong, and high levels of potential risk described herein.
In some
example, exception data 406 may also identify and characterize one or more
triggering
criterion that, when satisfied by portions of risk profile data 228 and risk
level data 242,
triggers a performance of one or more of the operations by monitoring system
130.
[0110] In one instance, exception data 406 may include notification parameters
408 that identify and characterize one or more notification operations capable
of
performance by monitoring system 130 upon detection of a particular level of
customer
risk, e.g., as specified within risk level data 242. Examples of these
notification
operation include, but are not limited to, a generation and transmission of a
customer-
specific notification to network-connected devices or systems operated by the
customers of the financial institution, employees or agents of the financial
institution,
and additionally, or alternatively, other business, governmental, or
regulatory entities
associated with the provisioned financial services (e.g., an underwriter of a
commercial
loan, a commercial lender, a governmental agency, etc.).
[0111] Further, in some instances, monitoring system 130 may also perform
operations that facilitate a review of the financial services provisioned to
one or more
customers, and the underlying risk factors associated with the provisioned
financial
services, in accordance with a predetermined or a periodic schedule, such as
on a
quarterly basis, a semi-annual basis, or a yearly basis. The performance of
these
operations may, for example, generate data indicative of a potential risk
resulting from
54
CA 3019195 2018-10-01
the provisioning of the financial services to certain customers, and enable
the financial
institution to identify those customers "at risk" of a defaulting on certain
provisioned
payment, credit, or other financial services. In some examples, exception data
406 may
also include review parameters 410 that establish a review schedule for
customers
segmented into each of the levels of potential customer risk, and further
specifies, for
each of the levels of customer risk, an intensity and a scope of the scheduled
review.
[0112] Referring to FIG. 4B, exception data 406 may include a plurality of
structured data records that maintain elements of notification parameters 408
and
review parameters 410 associated with each of the levels of potential customer
risk
described herein. By way of example, and for a low-risk customer (e.g., a
customer
associated with a low composite metric value, a minimal volatility in that
composite
metric value, and minimal total exposure value), data element 412A may specify
notification operations that include, but are not limited to, generating and
transmitting a
low-risk notification to a network-connected device or system operated by the
customer,
and further, may specify a light-intensity, yearly review that establishes
whether any
future general, financial, and behavioral risk factors indicate an increased
risk to the
financial institution.
[0113] Further, and for a customer characterized as a slight risk to the
financial
institution (e.g., a customer associated with increased composite metric
values,
volatility, and total exposure), data element 412B may specify notification
operations
that include, but are not limited to, generating and transmitting a slight-
risk notification to
a network-connected device or system operated by the customer, and may specify
a
yearly review of moderate intensity. By way of example, the moderate-intensity
review
may confirm both the current status of the general, financial, and behavioral
risk factors
CA 3019195 2018-10-01
for the customer and that any expected changes in these general, financial,
and
behavioral risk factors would reduce, or not increase, the potential risk to
the financial
institution.
[0114] For a customer characterized as a strong risk to the financial
institution
(e.g., a customer associated with a moderate composite metric value, a
moderate
volatility, and/or a high-value exposure), or as a high risk to the financial
institution (e.g.,
a customer associated with a highest composite metric value, volatility,
and/or
exposure), data elements 412C and 412D may each specify notification
operations that
include, but are not limited to, generating and transmitting a strong-risk
notification to a
network-connected device or system operated by the customer and further, to an
additional network-connected device or system operated by business,
governmental, or
regulatory entities associated with the provisioned financial services, e.g.,
an
underwriter or servicer of a commercial loan, etc.
[0115] For the strong-risk customer, data element 412C may specify a full
review
on a semi-annual basis, which identifies each of the payment, credit, or other
financial
instruments provisioned to the customer, and which characterizes a current and
future
impact of the underlying general, financial, and behavioral risk factors on
the potential
risk to the financial institution. Further, for the high-risk customer, data
element 412D
may specify an in-depth, quarterly review that not only identifies each of the
payment,
credit, or other financial instruments provisioned to the customer and
characterizes a
current and future impact of the underlying general, financial, and behavioral
risk factors
on the potential risk to the financial institution, but also reassesses the
acceptance of
the potential risk resulting from the provisioning of the financial services
to the high-risk
56
CA 3019195 2018-10-01
customer, e.g., through a modification to the terms of the provisioned
payment, credit,
or financial instruments.
[0116] The disclosed embodiments are, however, not limited to these exemplary
levels of potential risk, or to these examples of notification and review
parameters. In
other instances, the data records of exception data 406 may identify and
characterize
notification operations or review parameters consistent with any additional,
or alternate,
level of potential risk to the financial institution that would be appropriate
to the
provisioned financial services or to the customers. Further, in additional
instances, the
data records of exception data 406 may also identify and characterize any
additional, or
alternate, notification or review parameters (include a lack of a notification
or a lack of
review), and any additional, or alternate operations (including a modification
of the
terms of a provided payment or credit instrument) that would be appropriate to
the
levels of potential risk.
[0117] Referring back to FIG. 4A, exception data 406 may also include
triggering
data 414 associated with the elements of the elements of risk profile data 228
(e.g.,
composite metric values 224, temporal evolutions 234 in the composite metric
values,
and total exposure values 236 for each of the identified customers of the
financial
institution) and additionally, or alternatively, the elements of risk level
data 242. For
instance, triggering data 414 may identify and characterize one or more
operations
capable of performance by monitoring system 130, and may link the performance
of
each of the operations to a detection, by exception module 244, of a customer-
specific
triggering condition.
[0118] Examples of these customer-specific triggering conditions may include,
but are not limited to, a composite metric value, a temporal rate of change in
the
57
CA 3019195 2018-10-01
composite metric value, or a total exposure value of a particular customer
that exceeds
a corresponding threshold value, an assignment of a risk level to a particular
customer,
or an increase in the risk level assigned to the customer (e.g., an increase
in risk level
from slight to high, etc.). Further, examples of the triggered operations
include, but are
not limited to, a modification to a term associated with a provisioned payment
instrument (e.g., a commercial credit card, etc.) or a provisioned credit
instrument (e.g.,
a revolving line of credit, a commercial loan, etc.), an acceleration of a
scheduled
review, or an initiation of out-of-band communications by an employee of the
financial
institution, e.g., a telephone call, etc.
[0119] For instance, triggering data 414 may establish a customer-specified
triggering condition that includes, but is not limited to, a threshold amount
of credit
exposure for each of the commercial customers of the financial institution.
Triggering
data 414 may also specify that, upon a determination that the total exposure
value for a
particular one of the commercial customers exceeds the threshold amount,
monitoring
system 130 performs operations that include, but are not limited to, modifying
the terms
of one or more provisioned payment instruments or credit instruments to reduce
the
total exposure value below the threshold amount (e.g., by reducing an amount
of credit
available to the particular commercial customer through a revolving line of
credit, or by
increasing a variable interest rate associated with a commercial loan), and
generating
and transmitting an exception notification that identifies the triggering
condition and the
resulting modification to a network-connected device or system associated with
the
particular commercial customer, e.g., client device 102 of FIG. 1.
[0120] In other instances, triggering data 414 may establish a customer-
specific
triggering condition based on a detected change in a level of potential risk
across
58
CA 3019195 2018-10-01
multiple temporal intervals. For example, triggering data 414 may specify
that, in
response to a detected change in a customer's risk level from low or slight
risk to high
risk, monitoring system 130 performs operations that initiate an immediate, in-
depth
review of the payment, credit, or other financial instruments provisioned to a
corresponding customer, and that suspend the provisioning of any further
financial
services to that corresponding customer until completion of the in-depth
review, e.g., to
minimize future exposure to risk. The disclosed embodiments are, however, not
limited
to these exemplary triggering conditions and triggered operations, and in
other
instances, triggering data 414 may include any additional or alternate
triggering
conditions and triggered operations that would be appropriate to the elements
of risk
profile data 228 and risk level data 242, to the provisioned financial
services, and to the
individual or commercial customers of the financial institution.
[0121] Referring back to FIG. 4A, exception module 244 may perform operations
that parse risk profile data 228 to extract a corresponding one of customer
identifiers
402, composite metric values 224, temporal evolutions 234 in the composite
metric
values, and total exposure values 236 for each of the identified customers of
the
financial institution. Further, exception module 244 may also perform
operations that
parse risk level data 242, and extract a corresponding of the levels of
potential risk (e.g.,
the low, slight, strong, and high levels of potential risk described herein)
assigned to
each of the customers and associated with each of customer identifiers 402.
[0122] Based on the data records of exception data 406, exception module 244
may identify portions of review parameters 410 that are consistent with the
levels of
potential risk assigned to each of the identified customers of the financial
institution. As
described herein, review parameters 410 may specify, among other things, a
timing of a
59
CA 3019195 2018-10-01
scheduled review (e.g., yearly, semi-annually, quarterly, etc.) and an
intensity and a
scope of the scheduled review (e.g., the light, moderate, full, or in-depth)
that would be
consistent with the level of potential risk assigned to each of the identified
customers.
As illustrated in FIG. 4A, exception module 244 may perform operations that
associate
each of customer identifiers 402 with information that identifies the
corresponding
timing, intensity, or scope of the scheduled review, and that package customer
identifiers 402 and the associated information into corresponding portions of
scheduled
review data 418, which exception module 244 may store within the data records
of
monitoring database 136.
[0123] For example, for a particular one of the identified customers of the
financial institution (e.g., the commercial customer described herein), risk
level data 242
may indicate that the payment, credit, or other financial instruments
provisioned to that
particular customer represent a high risk to the financial institution. Based
on the data
records of exception data 406, exception module 244 may establish that the
scheduled
review for the particular commercial customer should correspond to an in-depth
review
conducted on a quarterly basis. As described herein, exception module 244 may
package a customer identifier of the particular commercial customer (e.g., a
corresponding one of customer identifiers 402) and information characterizing
the in-
depth, quarterly review for the particular customer into an element of
scheduled review
data 418, e.g., for storage within monitoring database 136.
[0124] Further, exception module 244 may also obtain triggering data 414 from
exception data 406, and parse triggering data 414 to identify one of the
customer-
specific triggering conditions and triggered operations. Exception module 244
may
perform additional operations that determine whether any of the customer-
specific
CA 3019195 2018-10-01
triggering conditions are consistent with a composite metric value (e.g., as
specified
within composite metric values 224), a temporal rate of change in the
composite metric
value (e.g., as specified within temporal evolutions 234), and a total
exposure value
(e.g., as specified within total exposure values 236) for one or more of the
identified
customers, and additionally or alternatively, with a risk level that
characterizes one or
more of the identified customers (e.g., as specified within risk level data
242). In some
instances, and in response to a determined consistency, exception module 244
may
initiate corresponding ones of the triggering operations for one or more of
the identified
customers.
[0125] By way of example, exception module 244 may determine that the total
risk exposure for the high-risk commercial customer described herein exceeds a
threshold amount of exposure (e.g., a specified triggering condition)
specified within
triggering data 414 and in response to the determination, exception module 244
may
perform operations that modify one or more terms of a provisioned payment or
credit
instrument to reduce the total exposure value of the high-risk commercial
customer
(e.g., an initiation of a corresponding triggered operation). In some
instances, exception
module 244 may obtain a customer identifier associated with the high-risk
commercial
customer (e.g., a corresponding one of customer identifiers 402), and based on
the
customer identifier, may access data 420 within account database 135 that
identifies
and characterizes one or more payment or credit instrument provisioned to the
high-risk
commercial customer.
[0126] For instance, the financial institution may provision a revolving line
of
credit to the high-risk commercial customer and may service a commercial loan
associated with the high-risk commercial customer, and data 420 may specify
values of
61
CA 3019195 2018-10-01
one or more parameters that characterize the revolving line of credit and the
commercial loan, e.g., amount of credit available to via the revolving line of
credit, and
interest rates associated with the revolving line-of-credit and the commercial
loan. In
some examples, exception module 244 may access data 420, and generate modified
parameter values 422 that, among other things, reduce the amount of credit
available
via the revolving line-of-credit and/or increase the interest rate of the
revolving line-of-
credit or the commercial loan. As described herein, the initiation and
performance of
these exemplary triggered operations by exception module 244 may dynamically
reduce
an exposure of the financial institution to the high-risk commercial customer
automatically and without intervention from employees of the financial
institution or from
the high-risk commercial customer.
[0127] Referring back to FIG. 4A, and based on the data records of exception
data 406, exception module 244 may also identify portions of notification
parameters
408 that are consistent with the levels of potential risk assigned to each of
the identified
customers of the financial institution. As described herein, notification
parameters 408
may specify that monitoring system 130 generate and transmit an appropriate
risk
notification to a network-connected device or system associated with each of
the
identified customers and in some instances, with a business, governmental, or
regulatory entity associated with one or more of the financial services
provisioned to
one or more of the identified customers. Exception module 244 may perform
operations
that associate each of the identified portions of notification parameters 408
with a
corresponding one of customer identifiers 402, and that provide the identified
portions of
notification parameters 408 and the associated customer identifiers as an
input to a
notification generation module 424 of monitoring system 130. Additionally, or
62
CA 3019195 2018-10-01
alternatively, exception module 244 may also provide all or a portion of risk
profile data
228 and risk level data 242 as inputs to notification generation module 424.
[0128] In some examples, notification generation module 424 may perform any of
the exemplary processes described herein to generate the appropriate risk
notification
for each of the identified customers in accordance with corresponding portions
of
notification parameters 408 and additionally, or alternatively, with
corresponding
portions of risk profile data 228 or risk level data 242. Notification
generation module
424 may receive notification parameters 408 (e.g., and additionally, or
alternatively, risk
profile data 228 or risk level data 242), and may generate notification data
426 for
transmission to a network-connected device or system associated with each of
the
identified customers of the financial institution, e.g., as specified by
corresponding ones
of customer identifiers 402, and in some instances, to an additional network-
connected
device or system operated by a business, governmental, or regulatory entity
associated
with the financial services provisioned to one or more of the identified
customers.
[0129] Notification data 426 may include, for each of the identified
customers,
data characterizing a corresponding one of the assigned levels of potential
risk, e.g., the
low-, slight-, strong-, or high-risk levels obtained from corresponding
portions of risk
level data 242. In further instances, generated notification data 426 may also
include
information characterizing the parameterized risk profile of each of the
identified
customers, including, but not limited to, corresponding ones of composite
metric values
224, temporal evolutions 234 in the composite metric values, and total
exposure values
236, e.g., as extracted from risk profile data 228.
[0130] Additionally, or alternatively, notification data 426 may also include,
for
one or more of the identified customers, data characterizing a change in the
assigned
63
CA 3019195 2018-10-01
level of potential risk, or in the parameterized risk profile (e.g., composite
metric values
224, temporal evolutions 234 in the composite metric values, and/or total
exposure
values 236), across prior temporal intervals. For instance, and for a
particular one of
the identified customers, a corresponding portion of notification data 426 may
include a
current level of potential risk assigned to the particular customers, along
with historical
risk data identifying the levels of potential risk assigned to the particular
customer during
prior temporal intervals, e.g., each month during a prior year.
[0131] In some examples, notification data 426 may also include interface or
layout data that, when processed by a corresponding one of the network-
connected
devices or systems, facilitates a presentation of a corresponding notification
within a
digital interface and improves an ability or an ease of a user, such as user
101 or 121,
to interact with or access that digital interface. For instance, the interface
or layout data
may assign, to each of the assigned levels of potential risk, a corresponding
symbol or
glyph that, when rendered for presentation within the digital interfaces by
the network-
connected devices or systems, enables a corresponding user to ascertain the
assigned
level or risk, or a change in the assigned level of risk, for a corresponding
customer of
the financial institution.
[0132] Further, and by way of example, the interface or layout data may
associate a particular color with each of the assigned levels of potential
risk, e.g., an
association of green to low-risk customer, yellow to a slight-risk customer,
orange to a
strong-risk customer, or red to a high-risk customer. In some instances, when
processed by a corresponding one of the network-connected devices or systems,
the
interface or layout data may cause the network-connected device or system to
present,
within a digital interface, information identifying a level of potential risk
assigned to a
64
CA 3019195 2018-10-01
corresponding customer, or a current or historical parameterization of the
risk profile of
that customer, in a color that is consistent with the assigned level of risk.
By presenting
a colored representation of the assigned level of potential risk, or of the
current or
historical parameterization of the risk profile, the exemplary embodiments
described
herein may enable a corresponding user, such as user 101 or 121, to perceive
visually
the assigned level of potential risk and to effectively interact with the
presented digital
interface, especially using network-connected devices having limited display
functionality.
[0133] Referring back to FIG. 4A, notification generation module 424 may
provide
notification data 426, which includes discrete elements of notification data
associated
with corresponding customer identifiers or with identifiers of corresponding
business,
governmental, or regulatory entities, to a routing module 428 of monitoring
system 130.
In some instances, routing module 428 may perform operations that parse
notification
data 426 to identify each of the customer identifiers (and additionally, or
alternatively,
information identifying the business, governmental, or regulatory entities)
associated
with corresponding and discrete portions of notification data 416.
[0134] Routing module 428 may access customer database 132, and may
identify and extract data identifying a network-connected device or system
(e.g., a
unique network address, such as an IP address, etc.) associated with each of
the
customer identifiers (and further, with the information identifying the
business,
governmental, or regulatory entities described herein). In some instances,
routing
module 428 may perform operations that cause monitoring system 130 to transmit
corresponding portions of notification data 426 to the unique network
addresses of the
network-connected devices or systems, e.g., to client devices 102 or 122,
which may
CA 3019195 2018-10-01
perform operations that render the corresponding portions of notification data
426 for
presentation within a digital interface in accordance with the interface or
layout data.
[0135] By way of example, and for the high-risk commercial customer described
herein, notification generation module 424 may perform any of the exemplary
processes
described herein to generate first high-risk notification 426A for
transmission to a
network-connected device or system associated with the commercial customer,
such as
client device 102 of FIG. 1. Further, and in accordance with portions of
notification
parameters 408, notification generation module 424 may also generate second
high-risk
notification 426B for transmission to one or more additional network-connected
devices
or systems operated by financial institutions or other business entities
associated with
the financial services provisioned to the commercial customer, e.g., the
commercial
credit card, the revolving line-of-credit, or the commercial loan.
Notification generation
module 424 may provide high-risk notifications 426A and 426B as inputs to
routing
module 428, which may perform any of the exemplary processes described herein
to
transmit first high-risk notification 426A to client device 102 and to
transmit second high-
risk notification 426B to the each of the one or more additional network-
connected
devices or systems (not illustrated in FIG. 4A).
[0136] In some examples, the network-connected devices or systems associated
with the identified customers (and additionally, or alternatively, the network-
connected
devices or systems operated by financial institutions or other business
entities
associated with certain of the provisioned financial services) may receive
corresponding
portions of notification data 426, e.g., via corresponding scure programmatic
interfaces. These network-connected devices or systems may each perform any of
the
exemplary processes described herein to render the corresponding portion of
66
CA 3019195 2018-10-01
notification data 426 for presentation within a digital interface and in
accordance with
the interface or layout data.
[0137] For example, in reference to FIG. 4C, a secure programmatic interface
of
client device 102, e.g., application programming interface (API) 430, may
receive high-
risk notification 426A. As described herein, high-risk notification 426A may
include,
among other things, data identifying the high-risk commercial customer (e.g.,
a
corresponding one of customer identifiers 402), data that characterizes risk
profile of the
high-risk customer (e.g., an indicator of the assigned high risk,
corresponding elements
of risk profile data 228, etc.), and corresponding elements of the interface
or layout data
described herein, In other instances, high-risk notification 426A may also
include
information that characterizes a time evolution of the risk profile of the
high-risk
customer, and additionally, or alternatively, that parameterizes the risk
profile within a
multidimensional risk space, such as risk space 320 of FIGs. 3B-3D.
[0138] API 430 may route high-risk notification 426A to an interface
processing
module 432 of executed banking application 108. In some instances, API 430 may
be
associated with or established by interface processing module 432, and may
facilitate
secure, module-to-module communications across network 120 between interface
processing module 432 and routing module 428 of monitoring system 130.
[0139] In some examples, interface processing module 432 may parse high-risk
notification 426A to extract data 434 characterizing the risk profile of the
high-risk
commercial customer (e.g., the assigned risk level, the composite metric
value, the
temporal evolution of that metric value, or the total exposure value), along
with all or a
portion of the interface and layout data described herein, e.g., interface and
layout data
436. As illustrated in FIG. 4C, interface processing module 432 may provide
risk data
67
CA 3019195 2018-10-01
434 and interface and layout data 436 as an input to an interface element
generation
module 438 of executed banking application 108. In one example, interface
element
generation module 438 may process risk data 434 and interface and layout data
436,
and may generate and route one or more interface elements 440 to display unit
116A of
client device 102, which may render interface elements 440 for presentation to
user 101
within a graphical user interface (GUI) 442.
[0140] In some instances, GUI 442 may represent a digital interface generated
by
executed banking application 108, and as illustrated in FIG. 4D, may include
interface
elements 444A that identify, to user 101, the high-level of risk that
characterizes the
commercial customer. Further, GUI 442 may also include additional interface
elements,
e.g., elements 444B, that characterize the parameterized risk profile of the
high-risk
commercial customer, and identify one or more of the composite metric value,
the
temporal evolution in that composite metric value, or the total exposure value
that
collectively establish the high-risk status of the commercial customer. In
some
instances, GUI 442 may present interface elements 444A or 444B in accordance
with a
visual characteristic associated with the assigned level of risk, e.g., as red
text
associated with high-risk status of the commercial customer. In other
instances, not
illustrated in FIG. 4D, GUI 442 may also include one or more symbols or glyphs
that
enable to the user to visually perceive the high-risk status of the commercial
customer,
and additional, or alternate, interface elements that present an evolution in
the risk
profile of the high-risk customer over various temporal intervals (e.g., over
a prior year)
or that graphically present the parameterized risk profile within a
corresponding,
multidimensional risk space.
68
CA 3019195 2018-10-01
[0141] In some examples, as described herein, monitoring system 130 may
perform operations that dynamically determine a level of potential risk that
characterizes
an interaction between a financial institution and one or more of its
individual or
commercial customers, and that dynamically parameterize a corresponding risk
profile
for each of these individual or commercial customers based not only on a
current
interaction between these customers and the financial institution, but on
changes in that
interaction over time. For instance, and using any of the processes described
herein,
monitoring system 130 may segment each of the individual or commercial
customers
into a corresponding one of the low, slight, strong, or high level of risk,
and perform
operations that tailor a scope and intensity scheduled review of the risk
profile for each
of the customers (e.g., the light, moderate, full, or in-depth reviews
described herein),
and that dynamically perform certain operation associated with each of the
customers,
in accordance with the determined low, slight, strong, or high levels of risk.
[0142] In further examples, and as described herein, monitoring system 130 may
perform additional operations that process portions of the customer-specific
risk levels
and the customer-specific risk profiles to generate values of aggregated
parameters that
characterize an aggregated risk profile of the financial institution. For
example,
monitoring system 130 may monitor and track a number of individual or
commercial
customers segmented into each of the determined levels of risk, and further,
may track
a temporal evolution of the number of segmented customers within each
determined
risk level on a month-to-month basis and further, on a year-to-year basis.
Monitoring
system 130 may also monitor and track a number of individual or commercial
customers
assigned to each of the review intensities and scopes, and may track a
temporal
69
CA 3019195 2018-10-01
evolution of the number of assigned customers on a month-to-month basis and
further,
on a year-to-year basis.
[0143] In some examples, monitoring system 130 may perform operations that
generate and transmit portions of the aggregated customer-specific data
described
herein to a network-connected device associated with an employee of agent of
the
financial institution, e.g., client device 122 of FIG. 1. As described herein,
client device
122 may receive the aggregated customer-specific data through a secure,
programmatic interface, and an application program executed by client device
122, such
as monitoring application 110 of FIG. 1, may perform any of the exemplary
processes
described herein to render the aggregated customer-specific data for
presentation
within a corresponding digital interface, such as a dashboard associated with
a
particular unit of the financial institution (e.g., a branch of the financial
institution).
[0144] Referring to FIG. 5, executed monitoring application 110 may present
the
digital interface, e.g., the branch-specific dashboard 500, via a
corresponding display
unit of client device 122, such as display unit 116A. As illustrated in FIG.
5, dashboard
500 may include interface elements 502 that identify and characterize the
segmentation
of individual or commercial customers into each of the levels of potential
risk described
herein (e.g., low, light, strong, and high levels of potential risk derived
from the provision
of financial services to the customers), and interface elements 522 that
identify and
characterize the scope and intensity of the scheduled review for the segmented
individual or commercial customers (e.g., light, moderate, full, and in-depth
reviews).
[0145] In some instances, executed monitoring application 110 may assign a
particular visual characteristic to each of the levels of potential risk
(e.g., green being
indicative of low risk, yellow being indicative of slight risk, orange being
indicative of
CA 3019195 2018-10-01
strong risk, and red being indicative of high risk) and additionally, or
alternatively, to
each of scope and intensity of the scheduled reviews (e.g., green being
indicative of a
light review, yellow being indicative of a moderate review, orange being
indicative of a
full review, and red being indicative of an in-depth review). The disclosed
embodiments
are, however, not limited to these exemplary visual characteristics, and in
other
instances, executed monitoring application 110 may assign any additional, or
alternate,
visual characteristic to the levels of potential risk or the scopes and
intensities of the
scheduled review within dashboard 500.
[0146] For example, interface elements 502 may include interface element 502A,
which indicates that seventy-four percent of the customers are characterized
as low-risk
customers, and that the total number of low-risk customers declined 0.66% on a
month-
to-month basis and 3.61% on a year-to-year basis. As illustrated in FIG. 5,
interface
element 502B indicates that nineteen percent of the customers are
characterized as
slight-risk customers, and that the total number of slight-risk customers
declined 0.22%
on a month-to-month basis, but increased 3.05% on a year-to-year basis.
Further,
interface element 502C which indicates that four percent of the customers are
characterized as strong-risk customers (e.g., representing increases of 0.82%
and
0.47% on respective ones of month-to-month and year-to-year basis), and
interface
element 502D indicates that three percent of the customers are characterized
as high-
risk customers (e.g., representing increases of 0.06% and 0.08% on respective
ones of
month-to-month and year-to-year basis). Interface element 502E plots an
evolution of
in a total number of low-, slight-, strong-, and high-risk customers on a
monthly basis
over a prior year.
71
CA 3019195 2018-10-01
[0147] Further, as illustrated in FIG. 5, interface elements 522 may also
include
interface element 522A, which plots a temporal evolution in a total number of
customers
scheduled for a light, moderate, full, or in-depth review on a monthly basis
over a prior
year. Additionally, interface elements 522B provide tabulated numbers of
triggered,
overdue, and completed ones of the light, moderate, full, or in-depth review
during not
only a current month, but also through the current year. The disclosed
embodiments
are, however, not limited to these examples of segmented customer data and
review
data, and to these exemplary interface elements, and in other instances,
dashboard 500
may include any additional or alternate number or type of interface elements
that
present any additional or alternate information to user 121.
[0148] FIG. 6 is a flowchart of an exemplary process 600 for dynamically
monitoring and profiling exchanges of data within an enterprise environment,
in
accordance with the disclosed embodiments. In some examples, a network-
connected
computing system, such as monitoring system 130 of FIG. 1, may perform one or
more
of the exemplary steps of process 600.
[0149] Referring to FIG. 6, monitoring system 130 may perform any of the
exemplary processes described herein to obtain data identifying one or more
counterparties to an exchange of data (e.g., in step 602). As described
herein, each of
the one or more counterparties may correspond to an individual or a commercial
customer of a financial institution that operates monitoring system 130, and
the obtained
data may include corresponding unique identifiers of these individual or
commercial
customers. Further, and as described herein, monitoring system 130 may obtain
the
customer identifiers from one or more locally accessible data repositories,
e.g., from
customer database 132 of FIG. 1.
72
CA 3019195 2018-10-01
[0150] Based on the obtained counterparty data, monitoring system 130 may
obtain contextual data that identifies and characterizes each of the
counterparties and
one or more data exchanges involving these counterparties (e.g., in step 604).
For
example, the obtained contextual data may include one or more elements of
customer
profile data, customer transaction data, and customer account data that
characterize
each of the identified customers, certain financial services provisioned to
each of the
identified customers, and certain transactions involving each of the customers
and/or
the provisioned financial services. In some instances, monitoring system 130
may
obtain all or a portion of the customer profile data, customer transaction
data, and
customer account data from one or more locally accessible data repositories
(e.g., from
customer database 132, transaction database 134, and account database 135 of
FIG.
1), or from one or more external computing systems across network 120, e.g.,
that
collectively establish a distributed, cloud-based data repository.
[0151] In some instances, monitoring system 130 may select one of the
identified
counterparties and identify portions of the contextual data that are
associated with the
selected counterparty (e.g., in step 606). Monitoring system 130 may apply one
or
more predictive models to the identified portions of the contextual data to
compute
values of a plurality of metrics that, collectively, indicate a likelihood
that the
counterparty performs an expected exchange of data in accordance with an
expected
parameter value during a corresponding and future temporal interval (e.g., in
step 608).
[0152] As described herein, the selected counterparty may correspond to one of
the customers of the financial institution (e.g., a commercial customer), and
the
performance of the expected data exchange may, in some examples, facilitate a
servicing of one or more existing obligations imposed on the commercial
customer by
73
CA 3019195 2018-10-01
the financial institution (e.g., a scheduled payment on a revolving line of
credit or a loan
provided to the customer by the financial institution). In some instances, the
plurality of
metric values computed for the commercial customer may be indicative of a risk
to the
financial institution that results from the provision of the financial
services to that
commercial customer, and each of the plurality of metric values may be
associated with
a correspond customer-specific risk factors, such as the general risk factor,
the financial
risk factor, and the behavioral risk factor described herein.
[0153] In some examples, and using any of the exemplary processes described
herein, monitoring system 130 may apply, to corresponding portions of the
customer
profile data, customer transaction data, and customer account data, a general
predictive
model that predicts a general metric value characterizing the general risk
factor for the
commercial customer, a financial predictive model that predicts a financial
metric value
characterizing the financial risk factor for the commercial customer, and a
behavioral
predictive model that predicts a behavioral metric value characterizing the
behavioral
risk factor for the commercial customer (e.g., in step 608). Further, and as
described
herein, the general, financial, and/or behavioral predictive models may
include, but are
not limited to, a deterministic statistical process, a stochastic statistical
process, a
machine learning process, or an artificial intelligence model.
[0154] For example, the deterministic statistical processes can include, but
are
not limited to, an index based on certain parameter values, a linear
regression model, a
nonlinear regression model, a multivariable regression model, and
additionally, or
alternatively, a linear or nonlinear least-squares approximation. Examples of
the
stochastic statistical process can include, among other things, a support
vector machine
(SVM) model, a multiple regression algorithm, a least absolute selection
shrinkage
74
CA 3019195 2018-10-01
operator (LASSO) regression algorithm, or a multinomial logistic regression
algorithm,
and examples of the machine learning processes can include, but are not
limited to, an
association-rule algorithm (such as an Apriori algorithm, an Eclat algorithm,
or an FP-
growth algorithm) or a clustering algorithm (such as a hierarchical clustering
process, a
k-means algorithm, or other statistical clustering algorithms). Further,
examples of the
artificial intelligence model include, but are not limited to, an artificial
neural network
model, a recurrent neural network model, a Bayesian network model, or a Markov
model.
[0155] Referring back to FIG. 6, monitoring system 130 may perform any of the
exemplary processes described herein to compute, for the commercial customer,
a
composite metric value based on a combination of the general metric value, the
financial metric value, and the behavioral metric value (e.g., in step 610).
As described
herein, the composite metric value may reflect a risk to the financial
institution that
results from a provisioning of financial services to the commercial customer,
and may
represent a relative contribution of the generate, financial, and behavioral
risk factors
described herein.
[0156] Further, in some instances, monitoring system 130 may perform any of
the
exemplary processes described herein that parameterize a multidimensional risk
profile
for the commercial customer based on the composite metric value, a time
evolution of
the composite metric value across one or more prior temporal intervals, and
additional
data characterizes an interaction between the identified customers and the
financial
institution (e.g., in step 612). For example, the additional data may include,
but is not
limited to, an exposure value that characterizes an amount of credit extended
to the
commercial customer by the financial institution, e.g., derived from certain
payment or
CA 3019195 2018-10-01
credit instruments issued to the commercial customer by the financial
institution. Based
on corresponding the composite metric value, the temporal evolution in the
composite
metric value, and the total exposure value, monitoring system 130 may perform
any of
the exemplary processes described herein to segment the commercial customer of
the
financial institution into a corresponding level of potential risk, e.g., low
risk, slight risk,
strong risk, or high risk (e.g., in step 614).
[0157] In some instances, monitoring system 130 may perform any of the
exemplary processes described herein to identify, and trigger an initiation
of, one or
more operations consistent with the level of potential risk assigned to the
commercial
customer of the financial institution and additionally, or alternatively, with
the
parameterized risk profile of the commercial customer (e.g., in step 616). As
described
herein, the one or more operations may include, but are not limited to, a
generation and
transmission of a customer-specific notification to network-connected devices
or
systems operated by the customers of the financial institution, employees or
agents of
the financial institution, and additionally, or alternatively, other business,
governmental,
or regulatory entities associated with the provisioned financial services
(e.g., an
underwriter of a commercial loan, a commercial lender, a governmental agency,
etc.).
[0158] In other instances, described herein, the one or more operations may
facilitate a review of the financial services provided to the commercial
customer, and
further, the determination of a timing, a scope, and an intensity of the
review for the
commercial customer (e.g., the light, moderate, full, or in-depth reviews
described
herein). Additionally, and as described herein, the one or more operations my
also
include, but are not limited to, a modification to a term associated with a
provisioned
payment instrument (e.g., a commercial credit card, etc.) or a provisioned
credit
76
CA 3019195 2018-10-01
instrument (e.g., a revolving line of credit, a commercial loan, etc.), an
acceleration of a
scheduled review, or an initiation of out-of-band communications by an
employee of the
financial institution, e.g., a telephone call, etc. The disclosed embodiments
are,
however, not limited to these examples of triggered operations, and in other
instances,
monitoring system 130 may initiate a performance of any additional or
alternate
operation appropriate to the determined risk level, and the parameterized risk
profile, of
the commercial customer.
[0159] Monitoring system 130 may further process the obtained customer data to
determine whether additional individual or commercial customers await
processing
using any of the exemplary processes described herein (e.g., in step 618). If
monitoring
system 130 were to identify additional individual or commercial customers
(step 618;
YES), exemplary process 600 may pass back to step 606, and monitoring system
130
may select an additional one of the identified customers for processing.
[0160] Alternatively, if monitoring system 130 were to establish that none of
the
individual or commercial customers await processing (e.g., step 618; NO),
monitoring
system 130 may package the customer identifiers, the determine risk levels,
and the
elements of parameterized risk profile data into corresponding elements of
output data,
which monitoring system 130 may storing within a locally accessible data
repository,
such as monitoring database 136 (e.g., in step 620). Exemplary process 600 is
then
complete is step 622.
Ill. Exemplary Hardware and Software Implementations
[0161] Embodiments of the subject matter and the functional operations
described in this specification can be implemented in digital electronic
circuitry, in
tangibly-embodied computer software or firmware, in computer hardware,
including the
77
CA 3019195 2018-10-01
structures disclosed in this specification and their structural equivalents,
or in
combinations of one or more of them. Embodiments of the subject matter
described in
this specification, including banking application 108, monitoring application
110,
predictive engine 138, initiation module 202, input processing module 206,
predictive
modules 215, general predictive module 216A, financial predictive module 2166,
behavioral predictive module 216C, aggregation module 222, risk
parameterization
module 226, risk segmentation module 238, exception module 244, notification
generation module 424, routing module 428, interface processing module 432,
and
interface element generation module 438, can be implemented as one or more
computer programs, i.e., one or more modules of computer program instructions
encoded on a tangible non transitory program carrier for execution by, or to
control the
operation of, a data processing apparatus (or a computer system).
[0162] Additionally, or alternatively, the program instructions can be encoded
on
an artificially generated propagated signal, such as a machine-generated
electrical,
optical, or electromagnetic signal that is generated to encode information for
transmission to suitable receiver apparatus for execution by a data processing
apparatus. The computer storage medium can be a machine-readable storage
device,
a machine-readable storage substrate, a random or serial access memory device,
or a
combination of one or more of them.
[0163] The terms "apparatus," "device," and "system" refer to data processing
hardware and encompass all kinds of apparatus, devices, and machines for
processing
data, including by way of example a programmable processor, a computer, or
multiple
processors or computers. The apparatus, device, or system can also be or
further
include special purpose logic circuitry, such as an FPGA (field programmable
gate
78
CA 3019195 2018-10-01
array) or an ASIC (application-specific integrated circuit). The apparatus,
device, or
system can optionally include, in addition to hardware, code that creates an
execution
environment for computer programs, such as code that constitutes processor
firmware,
a protocol stack, a database management system, an operating system, or a
combination of one or more of them.
[0164] A computer program, which may also be referred to or described as a
program, software, a software application, a module, a software module, a
script, or
code, can be written in any form of programming language, including compiled
or
interpreted languages, or declarative or procedural languages, and it can be
deployed in
any form, including as a stand-alone program or as a module, component,
subroutine,
or other unit suitable for use in a computing environment. A computer program
may,
but need not, correspond to a file in a file system. A program can be stored
in a portion
of a file that holds other programs or data, such as one or more scripts
stored in a
markup language document, in a single file dedicated to the program in
question, or in
multiple coordinated files, such as files that store one or more modules, sub-
programs,
or portions of code. A computer program can be deployed to be executed on one
computer or on multiple computers that are located at one site or distributed
across
multiple sites and interconnected by a communication network.
[0165] The processes and logic flows described in this specification can be
performed by one or more programmable computers executing one or more computer
programs to perform functions by operating on input data and generating
output. The
processes and logic flows can also be performed by, and apparatus can also be
implemented as, special purpose logic circuitry, such as an FPGA (field
programmable
gate array) or an ASIC (application-specific integrated circuit).
79
CA 3019195 2018-10-01
[0166] Computers suitable for the execution of a computer program include, by
way of example, general or special purpose microprocessors or both, or any
other kind
of central processing unit. Generally, a central processing unit will receive
instructions
and data from a read-only memory or a random-access memory or both. The
essential
elements of a computer are a central processing unit for performing or
executing
instructions and one or more memory devices for storing instructions and data.
Generally, a computer will also include, or be operatively coupled to receive
data from
or transfer data to, or both, one or more mass storage devices for storing
data, such as
magnetic, magneto-optical disks, or optical disks. However, a computer need
not have
such devices. Moreover, a computer can be embedded in another device, such as
a
mobile telephone, a personal digital assistant (PDA), a mobile audio or video
player, a
game console, a Global Positioning System (GPS) receiver, or a portable
storage
device, such as a universal serial bus (USB) flash drive, to name just a few.
[0167] Computer-readable media suitable for storing computer program
instructions and data include all forms of non-volatile memory, media and
memory
devices, including by way of example semiconductor memory devices, such as
EPROM, EEPROM, and flash memory devices; magnetic disks, such as internal hard
disks or removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks.
The processor and the memory can be supplemented by, or incorporated in,
special
purpose logic circuitry.
[0168] To provide for interaction with a user, embodiments of the subject
matter
described in this specification can be implemented on a computer having a
display unit,
such as a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for
displaying
information to the user and a keyboard and a pointing device, such as a mouse
or a
CA 3019195 2018-10-01
trackball, by which the user can provide input to the computer. Other kinds of
devices
can be used to provide for interaction with a user as well; for example,
feedback
provided to the user can be any form of sensory feedback, such as visual
feedback,
auditory feedback, or tactile feedback; and input from the user can be
received in any
form, including acoustic, speech, or tactile input. In addition, a computer
can interact
with a user by sending documents to and receiving documents from a device that
is
used by the user; for example, by sending web pages to a web browser on a
user's
device in response to requests received from the web browser.
[0169] Implementations of the subject matter described in this specification
can
be implemented in a computing system that includes a back-end component, such
as a
data server, or that includes a middleware component, such as an application
server, or
that includes a front-end component, such as a computer having a graphical
user
interface or a Web browser through which a user can interact with an
implementation of
the subject matter described in this specification, or any combination of one
or more
such back-end, middleware, or front-end components. The components of the
system
can be interconnected by any form or medium of digital data communication,
such as a
communication network. Examples of communication networks include a local area
network (LAN) and a wide area network (WAN), such as the Internet.
[0170] The computing system can include clients and servers. A client and
server are generally remote from each other and typically interact through a
communication network. The relationship of client and server arises by virtue
of
computer programs running on the respective computers and having a client-
server
relationship to each other. In some implementations, a server transmits data,
such as
an HTML page, to a user device, such as for purposes of displaying data to and
81
CA 3019195 2018-10-01
receiving user input from a user interacting with the user device, which acts
as a client.
Data generated at the user device, such as a result of the user interaction,
can be
received from the user device at the server.
[0171] While this specification includes many specifics, these should not be
construed as limitations on the scope of the invention or of what may be
claimed, but
rather as descriptions of features specific to particular embodiments of the
invention.
Certain features that are described in this specification in the context of
separate
embodiments may also be implemented in combination in a single embodiment.
Conversely, various features that are described in the context of a single
embodiment
may also be implemented in multiple embodiments separately or in any suitable
sub-
combination. Moreover, although features may be described above as acting in
certain
combinations and even initially claimed as such, one or more features from a
claimed
combination may in some cases be excised from the combination, and the claimed
combination may be directed to a sub-combination or variation of a sub-
combination.
[0172] Similarly, while operations are depicted in the drawings in a
particular
order, this should not be understood as requiring that such operations be
performed in
the particular order shown or in sequential order, or that all illustrated
operations be
performed, to achieve desirable results. In certain circumstances,
multitasking and
parallel processing may be advantageous. Moreover, the separation of various
system
components in the embodiments described above should not be understood as
requiring such separation in all embodiments, and it should be understood that
the
described program components and systems may generally be integrated together
in a
single software product or packaged into multiple software products.
82
CA 3019195 2018-10-01
[0173] In each instance where an HTML file is mentioned, other file types or
formats may be substituted. For instance, an HTML file may be replaced by an
XML,
JSON, plain text, or other types of files. Moreover, where a table or hash
table is
mentioned, other data structures (such as spreadsheets, relational databases,
or
structured files) may be used.
[0174] Various embodiments have been described herein with reference to the
accompanying drawings. It will, however, be evident that various modifications
and
changes may be made thereto, and additional embodiments may be implemented,
without departing from the broader scope of the disclosed embodiments as set
forth in
the claims that follow.
[0175] Further, other embodiments will be apparent to those skilled in the art
from
consideration of the specification and practice of one or more embodiments of
the
present disclosure. It is intended, therefore, that this disclosure and the
examples
herein be considered as exemplary only, with a true scope and spirit of the
disclosed
embodiments being indicated by the following listing of exemplary claims.
83
CA 3019195 2018-10-01
