DESC:TECHNICAL FIELD
The present disclosure relates generally to money laundering detection, and, more particularly, to automated system and method for anti-money laundering.
BACKGROUND
Money laundering is the process of converting large amount of money obtained from crimes, such as drug trafficking, into origination from a legitimate source. Money laundering requires an underlying, primary, profit-making crime (such as corruption, drug trafficking, market manipulation, fraud, tax evasion), along with the intent to conceal the proceeds of the crime or to further the criminal enterprise. Financial institutions are held to high standards with regards to following procedures to identify money laundering. All bank employees are trained to some degree to identify and monitor suspicious customer activity. Larger financial institutions will also have dedicated departments to track fraud and money laundering.
Artificial intelligence application in financial crimes is ever evolving. Using machine learning algorithms to optimize the workload of investigators and also make their investigation more effective has been the focus area for data scientists in the recent past. Inclusion of Artificial Intelligence and machine learning algorithms has improved the money laundering detection drastically. Machine learning techniques is the cornerstone of state-of-the-art anti-money laundering (AML) solutions both today and for the future of money laundering surveillance. It creates more efficient and effective teams by automating case enrichment and prioritization for investigators.
There are multiple typologies used in AML. From business perspective, typologies are essentially mechanisms used by money launderers. For e.g., small money cash deposits from multiple accounts to a single beneficiary; money wired in and majority of it wired out within short duration, international wire in from ASEAN nations and then wire out to South American nations; and many more. Generally, enterprise solutions capture them through set of rules/ scenarios. Machine learning models try to optimize this by capturing relevant patterns from various dimensions and combine them together for higher efficiency of tagging riskiness of transactions. Howsoever, there are many limitations of conventional technologies such as managing data and analytics is still a big task for the engineers, less IT capacities and capabilities, a major resistance of cloud computing solutions.
Thus, there is a requirement of an optimized and improved system and a method for efficient detection of money laundering to address the aforementioned problem of money laundering.
SUMMARY
In an aspect of the present disclosure, a data processing apparatus includes processing circuitry. The processing circuitry includes a classification engine. The processing circuitry is configured to generate processed unstructured data by pre-processing identified unstructured data based on a framework of the classifier engine. Further, the processing circuitry is configured to generate a three-dimensional feature vector for each dataset of the processed unstructured data based on first through third sets of parameters of the framework of the classifier engine. Furthermore, the processing circuitry is configured to determine a quality score of each dataset of the processed unstructured data by a comparison of the three-dimensional feature vector of each dataset with a set of predefined values to generate structured data, and segregate the structured data into first and second sets of data based on the quality score of each dataset of the processed unstructured data. Furthermore, the processing circuitry is configured to determine a set of relevant parameters of the first through third sets of parameters of the framework. Furthermore, the processing circuitry is configured to update the framework of the classifier engine for classification of input data into one or more classes based on the updated values of the set of relevant parameters and a set of threshold values of the set of relevant parameters. Furthermore, the processing circuitry is configured to classify, by way of the updated framework of the classifier engine, the input data into the one or more classes.
In some aspects, prior to the generation of the processed unstructured data, the processing circuitry is configured to determine an attribute of one or more attributes associated with each data sample of unstructured data, associate the determined attribute to each data sample of the unstructured data, select a problem statement and a sampling methodology for the identified data from a set of predefined problem statements and sampling methodologies, and generate the framework for the classifier engine based on the selected problem statement and the sampling methodology.
In some aspects, to generate the three-dimensional feature vector, the processing circuitry is configured to determine first through third sets of values of the first through third sets of parameters based on the framework of the classifier engine. The first through third sets of values of the first through third sets of parameters correspond to first through third dimension of the three-dimensional feature vector of each dataset of the processed unstructured data.
In some aspects, the first through third sets of parameters correspond to customer centric parameters, transaction centric parameters, and transaction network centric parameters, respectively, that are associated with the processed unstructured data.
In some aspects, to determine the set of relevant parameters of the first through third sets of parameters, the processing circuitry is configured to determine a transaction behavior of each data sample of the first set of data based on a univariate analysis of each parameter of the first through third sets of parameters, determine a criticality score of each parameter of the first through third sets of parameters based on the transaction behavior of each data sample of the first set of data, and update value of each parameter of the determined set of relevant parameters by way of one or more functional transformations.
In some aspects, prior to the update of the framework of the classifier engine, the processing circuitry is configured to determine an accuracy of the framework of the classifier engine for detection of abnormal transaction behavior using the second set of data and validate the accuracy of the framework for the detection of abnormal transaction behavior using one or more statistical validation techniques, when tested using the second set of data.
In some aspects, the processing circuitry is further configured to determine a risk score of each data entry of the input data based on the associated class and prioritize classification of the input data associated with at least one class of the one or more classes of the classifier engine based on the risk score of each data entry of the input data.
In another aspect of the present disclosure, a method includes generating, by way of processing circuitry, processed unstructured data by pre-processing identified unstructured data based on a framework of a classifier engine of the processing circuitry. The method further includes generating, by way of the processing circuitry, a three-dimensional feature vector for each dataset of the processed unstructured data based on first through third sets of parameters of the framework of the classifier engine. Furthermore, the method includes determining, by way of the processing circuitry, a quality score of each dataset of the processed unstructured data by a comparison of the three-dimensional feature vector of each dataset with a set of predefined values to generate structured data. Furthermore, the method includes segregating, by way of the processing circuitry, the structured data into first and second sets of data based on the quality score of each dataset of the processed unstructured data. Furthermore, the method includes determining, by way of the processing circuitry, a set of relevant parameters of the first through third sets of parameters of the framework. Furthermore, the method includes updating, by way of the processing circuitry, the framework of the classifier engine for classification of input data into one or more classes based on the updated values of the set of relevant parameters and a set of threshold values of the set of relevant parameters. Furthermore, the method includes classifying, by way of the updated framework of the classifier engine, the input data into the one or more classes.
BRIEF DESCRIPTION OF DRAWINGS
The above and still further features and advantages of aspects of the present disclosure becomes apparent upon consideration of the following detailed description of aspects thereof, especially when taken in conjunction with the accompanying drawings, and wherein:
FIG. 1 illustrates a block diagram of a system for anti-money laundering, in accordance with an exemplary aspect of the present disclosure;
FIG. 2 illustrates a block diagram of a data processing apparatus of the system of FIG. 1, in accordance with an exemplary aspect of the present disclosure; and
FIG. 3 illustrates a flow chart of a method for anti-money laundering, in accordance with an exemplary aspect of the present disclosure.
To facilitate understanding, like reference numerals have been used, where possible, to designate like elements common to the figures.
DETAILED DESCRIPTION
Various aspect of the present disclosure provides a system, an apparatus, and a method for anti-money laundering. The following description provides specific details of certain aspects of the disclosure illustrated in the drawings to provide a thorough understanding of those aspects. It should be recognized, however, that the present disclosure can be reflected in additional aspects and the disclosure may be practiced without some of the details in the following description.
The various aspects including the example aspects are now described more fully with reference to the accompanying drawings, in which the various aspects of the disclosure are shown. The disclosure may, however, be embodied in different forms and should not be construed as limited to the aspects set forth herein. Rather, these aspects are provided so that this disclosure is thorough and complete, and fully conveys the scope of the disclosure to those skilled in the art. In the drawings, the sizes of components may be exaggerated for clarity.
It is understood that when an element is referred to as being “on,” “connected to,” or “coupled to” another element, it can be directly on, connected to, or coupled to the other element or intervening elements that may be present. As used herein, the term “and/or” includes any and all combinations of one or more of the associated listed items.
The subject matter of example aspects, as disclosed herein, is described with specificity to meet statutory requirements. However, the description itself is not intended to limit the scope of this patent. Rather, the inventor/inventors have contemplated that the claimed subject matter might also be embodied in other ways, to include different features or combinations of features similar to the ones described in this document, in conjunction with other technologies. Generally, the various aspects including the example aspects relate to the system, an apparatus and the method for anti-money laundering.
As mentioned, there is a is a requirement of an optimized and improved system and a method for efficient detection of money laundering to address the problem of money laundering. The present aspects, therefore: provides a system 100, a data processing apparatus 104, and a method 300 that provides an improvised technical solution that overcomes the aforementioned problems.
The aspects herein and the various features and advantageous details thereof are explained more fully with reference to the non-limiting aspects that are illustrated in the accompanying drawings and detailed in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the aspects herein. The examples used herein are intended merely to facilitate an understanding of ways in which the aspects herein may be practiced and to further enable those of skill in the art to practice the aspects herein. Accordingly, the examples should not be construed as limiting the scope of the aspects herein.
FIG. 1 illustrates a block diagram of the system 100 for anti-money laundering, in accordance with an exemplary aspect of the present disclosure. The system 100 may include a user device 102 and a data processing apparatus 104. In some aspects of the present disclosure, the user device 102 may be communicatively coupled to the data processing apparatus 104 by way of either of, a first wired communication medium and a first wireless communication medium. In some aspects of the present disclosure, the user device 102 and the data processing apparatus 104 may be communicatively coupled to each other by way of a communication network 106.
In some aspects of the present disclosure, the user device 102 may include a user interface 110, a processing unit 112, a memory unit 114, a console 116, and a communication interface 118.
The user interface 110 may include an input interface (not shown) for receiving inputs from the user. In some aspects of the present disclosure, the input interface may be configured to enable the user to provide unstructured data to be processed by the data processing apparatus 104 for anti-money laundering. Further, the input interface may be configured to enable the user to select and/or provide inputs for registration and/or authentication of the user to use one or more functionalities of the system 100. In some aspects of the present disclosure, the input interface may be configured to enable the user to provide inputs to enable password protection for logging-in to the system 100. Examples of the input interface may include, but are not limited to, a touch interface, a mouse, a keyboard, a motion recognition unit, a gesture recognition unit, a voice recognition unit, or the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the input interface including known, related art, and/or later developed technologies. The user interface 110 may further include an output interface (not shown) for displaying (or presenting) an output to the user. In some aspects of the present disclosure, the first output interface may be configured to display, present or notify a condition of money laundering detected by the system 100 to the user. Examples of the output interface may include, but are not limited to, a digital display, an analog display, a touch screen display, a graphical user interface, a website, a webpage, a keyboard, a mouse, a light pen, an appearance of a desktop, and/or illuminated characters. Aspects of the present disclosure are intended to include and/or otherwise cover any type of the output interface including known and/or related, or later developed technologies.
The processing unit 112 may include suitable logic, instructions, circuitry, interfaces, and/or codes for executing various operations, such as the operations associated with the user device 102, and/or the like. In some aspects of the present disclosure, the processing unit 112 may utilize one or more processors such as Arduino or raspberry pi or the like. Further, the processing unit 112 may be configured to control one or more operations executed by the user device 102 in response to the input received at the user interface 110 from the user. Examples of the processing unit 112 may include, but are not limited to, an application-specific integrated circuit (ASIC) processor, a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a field-programmable gate array (FPGA), a Programmable Logic Control unit (PLC), and the like. Aspects of the present disclosure are intended to include or otherwise cover any type of processing unit 112 including known, related art, and/or later developed processing units.
The memory unit 114 may be configured to store the logic, instructions, circuitry, interfaces, and/or codes of the processing unit 112, data associated with the user device 102, and/or data associated with the system 100. In some aspects of the present disclosure, the memory unit 114 may be configured to store a variety of inputs received from the user. Examples of the memory unit 114 may include, but are not limited to, a Read-Only Memory (ROM), a Random-Access Memory (RAM), a flash memory, a removable storage drive, a hard disk drive (HDD), a solid-state memory, a magnetic storage drive, a Programmable Read Only Memory (PROM), an Erasable PROM (EPROM), and/or an Electrically EPROM (EEPROM). Aspects of the present disclosure are intended to include or otherwise cover any type of memory unit 114 including known, related art, and/or later developed memories.
The console 116 may be configured as a computer-executable application, to be executed by the processing unit 112. The console 116 may include suitable logic, instructions, and/or codes for executing various operations and may be controlled by the data processing apparatus 104. The one or more computer executable applications may be stored in the memory unit 114. Examples of the one or more computer executable applications may include, but are not limited to, an audio application, a video application, a social media application, a navigation application, or the like. Aspects of the present disclosure are intended to include or otherwise cover any type of the computer executable application including known, related art, and/or later developed computer executable applications.
The communication interface 118 may be configured to enable the user device 102 to communicate with the data processing apparatus 104. Examples of the communication interface 118 may include, but are not limited to, a modem, a network interface such as an Ethernet card, a communication port, and/or a Personal Computer Memory Card International Association (PCMCIA) slot and card, an antenna, a radio frequency (RF) transceiver, one or more amplifiers, a tuner, one or more oscillators, a digital signal processor, a coder-decoder (CODEC) chipset, a subscriber identity module (SIM) card, and a local buffer circuit. It will be apparent to a person of ordinary skill in the art that the communication interface 118 may include any device and/or apparatus capable of providing wireless or wired communications between the user device 102 and the data processing apparatus 104.
The data processing apparatus 104 may be a network of computers, a software framework, or a combination thereof, that may provide a generalized approach to create the server implementation. Examples of the data processing apparatus 104 may include, but are not limited to, personal computers, laptops, mini-computers, mainframe computers, any non-transient and tangible machine that can execute a machine-readable code, cloud-based servers, distributed server networks, or a network of computer systems. The data processing apparatus 104 may be realized through various web-based technologies such as, but not limited to, a Java web-framework, a .NET framework, a personal home page (PHP) framework, or any web-application framework. The data processing apparatus 104 may include processing circuitry 120 and one or more memory units (hereinafter, collectively referred to and designated as “Database 122”).
The processing circuitry 120 may include suitable logic, instructions, circuitry, interfaces, and/or codes for executing various operations of the system 100. The processing circuitry 120 may be configured to host and enable the console 112 running on (or installed on) the user device 102 to execute the operations associated with the system 100 by communicating one or more commands and/or instructions over the communication network 106. The processing circuitry 120 may be configured to determine a condition of money laundering by processing the unstructured data received by the processing circuitry 120. In some aspects of the present disclosure, the unstructured data for detection of money laundering may be received by the processing circuitry 120 by way of either of, the user device 102, an external server (not shown), or a combination thereof.
The database 122 may be configured to store the logic, instructions, circuitry, interfaces, and/or codes of the processing circuitry 120 for executing a number of operations. The database 122 may be further configured to store therein, data associated with users registered with the system 100. Some aspects of the present disclosure are intended to include and/or otherwise cover any type of the data associated with the users registered with the system 100. Examples of the database 122 may include but are not limited to, a ROM, a RAM, a flash memory, a removable storage drive, a HDD, a solid-state memory, a magnetic storage drive, a PROM, an EPROM, and/or an EEPROM. In some aspects of the present disclosure, the database 122 may be configured to store one or more of, user data, instructions data, processed data, notifications, and the like associated with the system 100.
The communication network 106 may include suitable logic, circuitry, and interfaces that may be configured to provide a number of network ports and a number of communication channels for transmission and reception of data related to operations of various entities (such as the user device 102, the data processing apparatus 104, and/or in some aspects, the external server (not shown)) of the system 100. Each network port may correspond to a virtual address (or a physical machine address) for transmission and reception of the communication data. For example, the virtual address may be an Internet Protocol Version 4 (IPV4) (or an IPV6 address) and the physical address may be a Media Access Control (MAC) address. The communication network 106 may be associated with an application layer for implementation of communication protocols based on one or more communication requests from the user device 102 and the data processing apparatus 104. The communication data may be transmitted or received, via the communication protocols. Examples of the communication protocols may include, but are not limited to, Hypertext Transfer Protocol (HTTP), File Transfer Protocol (FTP), Simple Mail Transfer Protocol (SMTP), Domain Network System (DNS) protocol, Common Management Interface Protocol (CMIP), Transmission Control Protocol and Internet Protocol (TCP/IP), User Datagram Protocol (UDP), Long Term Evolution (LTE) communication protocols, or any combination thereof.
In some aspects of the present disclosure, the communication data may be transmitted or received via at least one communication channel of a number of communication channels in the communication network 106. The communication channels may include, but are not limited to, a wireless channel, a wired channel, a combination of wireless and wired channel thereof. The wireless or wired channel may be associated with a data standard which may be defined by one of a Local Area Network (LAN), a Personal Area Network (PAN), a Wireless Local Area Network (WLAN), a Wireless Sensor Network (WSN), Wireless Area Network (WAN), Wireless Wide Area Network (WWAN), a metropolitan area network (MAN), a satellite network, the Internet, an optical fiber network, a coaxial cable network, an infrared (IR) network, a radio frequency (RF) network, and a combination thereof. Aspects of the present disclosure are intended to include or otherwise cover any type of communication channel, including known, related art, and/or later developed technologies.
In operation, the data processing apparatus 104, by way of the processing circuitry 120 may be configured to receive the unstructured data from either of, the user device 102, the external server (not shown) or a combination thereof. The data processing apparatus 102, by way of the processing circuitry 120, may further be configured to generate identified unstructured data based on one or more attributes of the unstructured data. Furthermore, the data processing apparatus 104, by way of the processing circuitry 120, may be configured to generate processed unstructured data by pre-processing identified unstructured data based on a framework of the classifier engine 212. Upon generation of the processed unstructured data, the data processing apparatus 104, by way of the processing circuitry 120, may be configured to generate a three-dimensional feature vector for each dataset of the processed unstructured data based on first through third sets of parameters of the framework of a classifier engine (shown later in FIG. 2 as ‘212’) of the processing circuitry 120. The data processing apparatus 104, by way of the processing circuitry 120, may further be configured to determine a quality score of each dataset of the processed unstructured data by a comparison of the three-dimensional feature vector of each dataset with a set of predefined values to generate structured data. Furthermore, the data processing apparatus 104, by way of the processing circuitry 120, may be configured to segregate the structured data into first and second sets of data based on the quality score of each dataset of the processed unstructured data. Upon segregation of the structured data, the data processing apparatus 104, by way of the processing circuitry 120, may be configured to determine a set of relevant parameters of the first through third sets of parameters of the framework. The data processing apparatus 104, by way of the processing circuitry 120, may further be configured to update the framework of the classifier engine 212 for classification of input data into one or more classes based on the updated values of the set of relevant parameters and a set of threshold values of the set of relevant parameters. Furthermore, the data processing apparatus 104, by way of the processing circuitry 120, may be configured to classify the input data into the one or more classes, by way of the updated framework of the classifier engine 212. In some aspects of the present disclosure, upon classification of the input data, the data processing apparatus 104, by way of processing circuitry 120 may be configured to determine a risk score of each data entry of the input data based on the associated class and prioritize the classification of the input data associated with at least one class of the one or more classes of the classifier engine 212 based on the risk score of each data entry of the input data.
FIG. 2 is a block diagram that illustrates the data processing apparatus 104 of FIG. 1, in accordance with an exemplary aspect of the present disclosure. The data processing apparatus 104 may include the processing circuitry 120 and the database 122. The data processing apparatus 104 may further include a network interface 200 and an input/output (I/O) interface 202. The processing circuitry 120, the database 122, the network interface 200, and the input/output (I/O) interface 202 may be configured to communicate with each other by way of a first communication bus 203.
In an exemplary aspect of the present disclosure, the processing circuitry 120 may include a data exchange engine 204, a registration engine 206, an authentication engine 208, a data processing engine 210, the classifier engine 212, a prioritization engine 214, and a notification engine 216 communicatively coupled to each other by way of a second communication bus 220. It will be apparent to a person having ordinary skill in the art that the data processing apparatus 104 is for illustrative purposes and not limited to any specific combination of hardware circuitry and/or software.
The data exchange engine 204 may be configured to enable transfer of data from the database 160 to various engines of the processing circuitry 158. The data exchange engine 204 may further be configured to enable transfer of data and/or instructions from the user device 102 to the data processing apparatus 104.
The registration engine 206 may be configured to enable the user to register into the system 100 by providing registration data through a registration menu (not shown) of the console 112 that may be displayed by way of the user device 102.
The authentication engine 208 by way of the data exchange engine 204 may be configured to fetch the registration data of the user and authenticate the registration data of the user. The authentication engine 208, upon successful authentication of the registration data of the user, may be configured to enable the user to log-in or sign up to the system 100. In some aspects of the present disclosure, the authentication engine 208 may enable the user to set the password protection for logging-in to the system 100. In such a scenario, the authentication engine 208 may be configured to verify a password entered by the user for logging-in to the system 100 by comparing the password entered by the user with the set password protection. In some aspects, when the password entered by the user is verified by the authentication engine 208, the authentication engine 208 may enable the user to log-in to the system 100. In some other aspects of the present disclosure, when the password entered by the user is not verified by the authentication engine 208, the authentication engine 208 may generate a signal for the notification engine 216 to generate a login failure notification for the user.
The data processing engine 210 may be configured to receive the unstructured data from the user device 102. Upon the reception of the unstructured data, yhe data processing engine 210 may be configured to determine an attribute of one or more attributes associated with each data sample of the unstructured data. In some aspects of the present disclosure, the one or more attributes may be dependent on one or more types of data samples of the unstructured data. The data processing engine 210 may further be configured to associate the determined attribute to each data sample of the unstructured data to generate the identified unstructured data.
The data processing engine 210 may further be configured to pre-process the identified unstructured data to generate processed unstructured data based on the framework of the classifier engine 212. In some aspects of the present disclosure, to pre-process the identified unstructured data the data processing engine 210 may be configured to select a problem statement and a sampling methodology for the identified data from a set of predefined problem statements and sampling methodologies. The data processing engine 210 may further generate the framework for the classifier engine 212 based on the selected problem statement and the sampling methodology.
Upon the generation of the processed unstructured data, the data processing engine 210 may be configured to generate the three-dimensional feature vector for each dataset of the processed unstructured data based on the first through third sets of parameters of the framework of the classifier engine.
In some aspects of the present disclosure, to generate the three-dimensional feature vector, the processing circuitry 120 may be configured to determine first through third sets of values of the first through third sets of parameters based on the framework of the classifier engine 212 such that the first through third sets of values of the first through third sets of parameters correspond to first through third dimension of the three-dimensional feature vector of each dataset of the processed unstructured data.
In some aspects of the present disclosure, the first through third sets of parameters correspond to customer centric parameters, transaction centric parameters, and transaction network centric parameters, respectively, that are associated with the processed unstructured data. Examples of the customer centric parameters may include but not limited to details of a customer related to demography, job, immigration, industry, and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of customer centric parameters without deviating from the scope of the present disclosure. Examples of the transaction centric parameters may include but not limited to, modes of payments, various derived factors capturing velocity, size, structuring of payments, and the like. Aspects of the present disclosure are intended to include and/or otherwise cover any type of transaction centric parameters without deviating from the scope of the present disclosure. Examples of the transaction network centric parameters may include but not limited to, parameters related to transparency, strength, trust etc. between different customers and the recipient’s accounts. Aspects of the present disclosure are intended to include and/or otherwise cover any type of transaction network centric parameters without deviating from the scope of the present disclosure.
Upon generation of the three-dimensional feature vector of each dataset of the processed unstructured, the data processing engine 210 may be configured to compare the three-dimensional feature vector of each dataset with the set of predefined values to generate structured data. The data processing engine 210 may further be configured to determine the quality score of each dataset of the processed unstructured data based on the comparison. Furthermore, the data processing engine 210 may be configured to segregate the structured data into the first and second sets of data based on the quality score of each dataset of the processed unstructured data.
Upon segregation of the structured data into the first and second sets of data based, the data processing engine 210 may be configured to determine the set of relevant parameters of the first through third sets of parameters of the framework of the classifier engine 212.
In some aspects of the present disclosure, to determine the set of relevant parameters of the first through third sets of parameters, the data processing engine 210 may be configured to determine a transaction behavior of each data sample of the first set of data based on a univariate analysis of each parameter of the first through third sets of parameters. The data processing engine 210 may further be configured to determine a criticality score of each parameter of the first through third sets of parameters based on the transaction behavior of each data sample of the first set of data. Furthermore, the data processing engine 210 may be configured to update a value of each parameter of the determined set of relevant parameters by way of one or more functional transformations.
In some aspects of the present disclosure, the data processing engine 210 may further be configured to determine an accuracy of the framework of the classifier engine 212 for detection of abnormal transaction behavior using the second set of data. Furthermore, the data processing engine 210 may be configured to validate the accuracy of the framework of the classifier engine 212 for the detection of abnormal transaction behavior using one or more statistical validation techniques, when tested using the second set of data.
Upon validation of the accuracy of the framework of the classifier engine 212, the data processing engine 210 may be configured to update the framework of the classifier engine 212 for classification of input data into one or more classes based on the updated values of the set of relevant parameters and the set of threshold values of the set of relevant parameters. In some aspects of the present disclosure, the data processing engine 210 may enable the user to provide the set of threshold values to the set of relevant parameters for classification of the data. In other aspects of the present disclosure, the set of threshold values of the set of relevant parameters may be pre-defined.
After the update of the framework of the classifier engine 212, the framework of the classifier engine 212 is ready for detection of abnormal transaction behavior of any data. The data processing engine 210 further provides the framework to the classifier engine 212.
Upon reception of the updated framework from the data processing engine, the classifier engine 212 may update a set of weights and a set of layers of a model of the classifier engine 212 based on the updated framework. The classifier engine 212 may further be configured to classify (by way of the updated framework of the classifier engine 212) the input data into the one or more classes. In some aspects of the present disclosure, the classifier engine 212 may be developed using one or more Artificial Intelligence (AI) and/or Machine Learning (ML) techniques.
The prioritization engine 214 may be configured to determine a risk score of each data entry of the input data based on the associated class. The prioritization engine 214 may further be configured to prioritize the classification of the input data associated with at least one class of the one or more classes of the classifier engine 212 based on the risk score of each data entry of the input data. In some aspects of the present disclosure, the prioritization engine 214 may alter the model of the classifier engine 212 based on the prioritization of the one or more classes. In some aspects of the present disclosure, the prioritization engine 214 may enable the user to assign a priority to at least one class of the one or more classes of classification. In some other aspects of the present disclosure, the priority of each class of the one or more classes may be pre-defined. In an exemplary aspect of the present disclosure, the one or more classes may include high-risk, medium-risk and low-risk transaction classes. The prioritization engine 214 may be configured to prioritize investigation of the high-risk and the medium-risk transactions over the low-risk transaction class by altering the model of the classifier engine 212 for the same.
The notification engine 218 may be configured to generate one or more notifications corresponding to the system 100 that may be presented to the user by way of the user device 102. It will be apparent to a person skilled in the art that the aspects of the present disclosure are intended to include or cover any type of notification generated by the system 100 and/or presented to the user by the system 100.
The database 122 may be configured to store data corresponding to the system 100. In some aspects of the present disclosure, the database 122 may be segregated into one or more repositories that may be configured to store a specific type of data. In an exemplary aspect of the present disclosure, the database 122 may include an instructions repository 222, a user data repository 224, a processed data repository 226, an anomaly repository, and a classes repository 230.
The instructions repository 222 may be configured to store instructions data corresponding to the data processing apparatus 104. The instructions data may include data and metadata of one or more instructions corresponding to the various entities of the data processing apparatus 104 such as the processing circuitry 120, the I/O interface 200 and/or the network interface 202. It will be apparent to a person skilled in the art that the aspects of the present disclosure are intended to include or cover any type of instructions data of the data processing apparatus 104, and thus must not be considered as a limitation of the present disclosure.
The user data repository 224 may be configured to store user data of the system 100. The user data may include data and metadata of the data of authenticated users that are registered on the system 100. In some aspects of the present disclosure, the user data repository 224 may further be configured to store partial data and/or partial metadata of the user data corresponding to users that fail to register and/or authenticate on the system 100. Furthermore, the user data repository 224 may be configured to store the set of inputs received from the user by way of the user device 102. It will be apparent to a person skilled in the art that the aspects of the present disclosure are intended to include or cover any type of user data and/or metadata of the user data of the system 100, and thus must not be considered as a limitation of the present disclosure. The processed data repository 226 may be configured to store the data generated by the data processing engine 210. In some aspects of the present disclosure, the processed data repository 226 may be configured to store therein, the identified unstructured data, the processed unstructured data, the structured data, the input data and the like. The anomaly repository 228 may be configured to store data related to anomaly of data corresponding to detection of money laundering. The classes repository 230 may be configured to store therein data of the one or more classes. The classes repository 230 may further be configured to store metadata of the classes that may include priority of each class of the one or more classes, risk score of the input data, the set of threshold values for the one or more classes, and the like. In some other aspects of the present disclosure, the database 122 may have a combined memory storage to store therein cumulative data as disclosed herein.
FIG. 3 illustrates a flow chart of a method 300 for anti-money laundering, in accordance with an exemplary aspect of the present disclosure.
At step 302, the data processing apparatus 104 may generate the processed unstructured data by pre-processing the identified unstructured data based on the framework of the classifier engine 212.
In some aspects of the present disclosure, to pre- processing the identified unstructured data, the data processing apparatus 104 may determine the attribute of the one or more attributes associated with each data sample of the unstructured data, associate the determined attribute to each data sample of the unstructured data, select the problem statement and the sampling methodology for the identified data from a set of predefined problem statements and sampling methodologies, and generate the framework for the classifier engine 212 based on the selected problem statement and the sampling methodology.
At step 304, the data processing apparatus 104 may generate the three-dimensional feature vector for each dataset of the processed unstructured data based on the first through third sets of parameters of the framework of the classifier engine 212.
In some aspects of the present disclosure, to generate the three-dimensional feature vector, the data processing apparatus 104 may determine first through third sets of values of the first through third sets of parameters based on the framework of the classifier engine 212.
At step 306, the data processing apparatus 104 may determine the quality score of each dataset of the processed unstructured data by the comparison of the three-dimensional feature vector of each dataset with the set of predefined values to generate the structured data.
At step 308, the data processing apparatus 104 may segregate the structured data into the first and second sets of data based on the quality score of each dataset of the processed unstructured data.
At step 310, the data processing apparatus 104 may determine the set of relevant parameters of the first through third sets of parameters of the framework.
In some aspects of the present disclosure, to determine the set of relevant parameters of the first through third sets of parameters, the data processing apparatus 104 may determine the transaction behavior of each data sample of the first set of data based on the univariate analysis of each parameter of the first through third sets of parameters. The data processing apparatus 104 may further determine the criticality score of each parameter of the first through third sets of parameters based on the transaction behavior of each data sample of the first set of data. Furthermore, the data processing apparatus 104 may update a value of each parameter of the determined set of relevant parameters by way of the one or more functional transformations.
At step 312, the data processing apparatus 104 may update the framework of the classifier engine 212 for classification of the input data into the one or more classes based on the updated values of the set of relevant parameters and the set of threshold values of the set of relevant parameters.
At step 314, the data processing apparatus 104 may classify, by way of the updated framework of the classifier engine 212, the input data into the one or more classes.
In some aspects of the present disclosure, the data processing apparatus 104 may determine a risk score of each data entry of the input data based on the associated class and prioritize the classification of the input data associated with at least one class of the one or more classes of the classifier engine 212 based on the risk score of each data entry of the input data. The prioritization of at least one class of the one or more classes may result in update of the model of the classifier engine 212 prior to the classification of the input data.
As mentioned, there is a is a requirement of an optimized and improved system and a method for efficient detection of money laundering to address the problem of money laundering. The present aspects, therefore: provides the system 100, the data processing apparatus 104, and the method 300 that provides an improvised technical solution that overcomes the aforementioned problems. The data processing apparatus 104 by way of the processing circuitry 120 provides a 360-degree view of transactions (in the unstructured data) by way of the three-dimensional feature vector determining metadata of the unstructured data in three different perspectives (i.e., through customer centric parameters, transaction centric parameters, and transaction network centric parameters), providing a structure to the unstructured data that is further used for finalizing the model and training of the classifier engine 212 for detection of money laundering. The processing circuitry 120 further enables the system 100 to assess every transaction with high accuracy of classification in near real time, and thus enables blocking transactions involving money-laundering in real time when observed to be a high-risk money laundering transaction.
The foregoing discussion of the present disclosure has been presented for purposes of illustration and description. It is not intended to limit the present disclosure to the form or forms disclosed herein. In the foregoing Detailed Description, for example, various features of the present disclosure are grouped together in one or more aspects, configurations, or aspects for the purpose of streamlining the disclosure. The features of the aspects, configurations, or aspects may be combined in alternate aspects, configurations, or aspects other than those discussed above. This method of disclosure is not to be interpreted as reflecting an intention the present disclosure requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed aspect, configuration, or aspect. Thus, the following claims are hereby incorporated into this Detailed Description, with each claim standing on its own as a separate aspect of the present disclosure.
Moreover, though the description of the present disclosure has included description of one or more aspects, configurations, or aspects and certain variations and modifications, other variations, combinations, and modifications are within the scope of the present disclosure, e.g., as may be within the skill and knowledge of those in the art, after understanding the present disclosure. It is intended to obtain rights which include alternative aspects, configurations, or aspects to the extent permitted, including alternate, interchangeable and/or equivalent structures, functions, ranges or steps to those claimed, whether or not such alternate, interchangeable and/or equivalent structures, functions, ranges or steps are disclosed herein, and without intending to publicly dedicate any patentable subject matter.
As one skilled in the art will appreciate, the system 100 includes a number of functional blocks in the form of a number of units and/or engines. The functionality of each unit and/or engine goes beyond merely finding one or more computer algorithms to carry out one or more procedures and/or methods in the form of a predefined sequential manner, rather each engine explores adding up and/or obtaining one or more objectives contributing to an overall functionality of the system 100. Each unit and/or engine may not be limited to an algorithmic and/or coded form, rather may be implemented by way of one or more hardware elements operating together to achieve one or more objectives contributing to the overall functionality of the system 100. Further, as it will be readily apparent to those skilled in the art, all the steps, methods and/or procedures of the system 100 are generic and procedural in nature and are not specific and sequential.
Certain terms are used throughout the following description and claims to refer to particular features or components. As one skilled in the art will appreciate, different persons may refer to the same feature or component by different names. This document does not intend to distinguish between components or features that differ in name but not structure or function. While various aspects of the present disclosure have been illustrated and described, it will be clear that the present disclosure is not limited to these aspects only. Numerous modifications, changes, variations, substitutions, and equivalents will be apparent to those skilled in the art, without departing from the spirit and scope of the present disclosure, as described in the claims. ,CLAIMS:1. A data processing apparatus (104) comprising:
processing circuitry (120) comprising a classifier engine (212), wherein the processing circuitry (120) is configured to (i) generate processed unstructured data by pre-processing identified unstructured data based on a framework of the classifier engine (212), (ii) generate a three-dimensional feature vector for each dataset of the processed unstructured data based on first through third sets of parameters of the framework of the classifier engine (212), (iii) determine a quality score of each dataset of the processed unstructured data by a comparison of the three-dimensional feature vector of each dataset with a set of predefined values to generate structured data (iv) segregate the structured data into first and second sets of data based on the quality score of each dataset of the processed unstructured data, (v) determine a set of relevant parameters of the first through third sets of parameters of the framework, (vi) update the framework of the classifier engine (212) for classification of input data into one or more classes based on the updated values of the set of relevant parameters and a set of threshold values of the set of relevant parameters, and (vii) classify, by way of the updated framework of the classifier engine (212), the input data into the one or more classes.

2. The data processing apparatus (104) as claimed in claim 1, wherein, prior to the generation of the processed unstructured data, the processing circuitry (120) is configured to (i) determine an attribute of one or more attributes associated with each data sample of unstructured data, (ii) associate the determined attribute to each data sample of the unstructured data, (iii) select a problem statement and a sampling methodology for the identified data from a set of predefined problem statements and sampling methodologies, and (iv) generate the framework for the classifier engine (212) based on the selected problem statement and the sampling methodology.

3. The data processing apparatus (104) as claimed in claim 1, wherein, to generate the three-dimensional feature vector, the processing circuitry (120) is configured to determine first through third sets of values of the first through third sets of parameters based on the framework of the classifier engine (212), wherein the first through third sets of values of the first through third sets of parameters correspond to first through third dimension of the three-dimensional feature vector of each dataset of the processed unstructured data.

4. The data processing apparatus (104) as claimed in claim 1, wherein the first through third sets of parameters correspond to customer centric parameters, transaction centric parameters, and transaction network centric parameters, respectively, that are associated with the processed unstructured data.

5. The data processing apparatus (104) as claimed in claim 1, wherein, to determine the set of relevant parameters of the first through third sets of parameters, the processing circuitry (120) is configured to (i) determine a transaction behavior of each data sample of the first set of data based on a univariate analysis of each parameter of the first through third sets of parameters, (ii) determine a criticality score of each parameter of the first through third sets of parameters based on the transaction behavior of each data sample of the first set of data, and (iii) update a value of each parameter of the determined set of relevant parameters by way of one or more functional transformations.

6. The data processing apparatus (104) as claimed in claim 1, wherein, prior to the update of the framework of the classifier engine (212), the processing circuitry (120) is configured to (i) determine an accuracy of the framework of the classifier engine (212) for detection of abnormal transaction behavior using the second set of data and (ii) validate the accuracy of the framework for the detection of abnormal transaction behavior using one or more statistical validation techniques, when tested using the second set of data.
7. The data processing apparatus (104) as claimed in claim 1, wherein, the processing circuitry (120) is further configured to (i) determine a risk score of each data entry of the input data based on the associated class and (ii) prioritize the classification of the input data associated with at least one class of the one or more classes of the classifier engine (212) based on the risk score of each data entry of the input data.

8. A method (300) comprising:
generating, by way of processing circuitry (120), processed unstructured data by pre-processing identified unstructured data based on a framework of a classifier engine (212) of the processing circuitry (120);
generating, by way of the processing circuitry (120), a three-dimensional feature vector for each dataset of the processed unstructured data based on first through third sets of parameters of the framework of the classifier engine (212);
determining, by way of the processing circuitry (120), a quality score of each dataset of the processed unstructured data by a comparison of the three-dimensional feature vector of each dataset with a set of predefined values to generate structured data;
segregating, by way of the processing circuitry (120), the structured data into first and second sets of data based on the quality score of each dataset of the processed unstructured data;
determining, by way of the processing circuitry (120), a set of relevant parameters of the first through third sets of parameters of the framework;
updating, by way of the processing circuitry (120), the framework of the classifier engine (212) for classification of input data into one or more classes based on the updated values of the set of relevant parameters and a set of threshold values of the set of relevant parameters; and
classifying, by way of the updated framework of the classifier engine (212), the input data into the one or more classes.

9. The method (300) as claimed in claim 8, wherein, prior to generating the processed unstructured data, the method (300) comprising (i) determining, by way of processing circuitry (120), an attribute of one or more attributes associated with each data sample of unstructured data, (ii) associating, by way of processing circuitry (120), the determined attribute to each data sample of the unstructured data, (iii) selecting, by way of processing circuitry (120), a problem statement and a sampling methodology for the identified data from a set of predefined problem statements and sampling methodologies, and (iv) generating, by way of processing circuitry (120), the framework for the classifier engine (212) based on the selected problem statement and the sampling methodology.

10. The method (300) as claimed in claim 8, wherein, for generating the three-dimensional feature vector, the method (300) comprising determining, by way of the processing circuitry (120), first through third sets of values of the first through third sets of parameters based on the framework of the classifier engine (212), wherein the first through third sets of values of the first through third sets of parameters correspond to first through third dimension of the three-dimensional feature vector of each dataset of the processed unstructured data.

11. The method (300) as claimed in claim 8, wherein the first through third sets of parameters correspond to customer centric parameters, transaction centric parameters, and transaction network centric parameters, respectively, that are associated with the processed unstructured data.

12. The method (300) as claimed in claim 8, wherein for determining the set of relevant parameters of the first through third sets of parameters, the method (300) comprising (i) determining, by way of the processing circuitry (120), a transaction behavior of each data sample of the first set of data based on a univariate analysis of each parameter of the first through third sets of parameters, (ii) determining, by way of the processing circuitry (120), a criticality score of each parameter of the first through third sets of parameters based on the transaction behavior of each data sample of the first set of data, and (iii) updating, by way of the processing circuitry (120), a value of each parameter of the determined set of relevant parameters by way of one or more functional transformations.

13. The method (300) as claimed in claim 8, wherein, prior to the updating the framework of the classifier engine (212), the method (300) comprising (i) determining, by way of the processing circuitry (120), an accuracy of the framework of the classifier engine (212) for detection of abnormal transaction behavior using the second set of data and (ii) validating, by way of the processing circuitry (120), the accuracy of the framework for the detection of abnormal transaction behavior using one or more statistical validation techniques, when tested using the second set of data.

14. The method (300) as claimed in claim 8, wherein the method (300) further comprising (i) determining, by way of the processing circuitry (120), a risk score of each data entry of the input data based on the associated class and (ii) prioritizing, by way of the processing circuitry (120), the classification of the input data associated with at least one class of the one or more classes of the classifier engine (212) based on the risk score of each data entry of the input data.