Claims:
WE CLAIM:
1. A processor-implemented method to recommend a credit decision based on a cognitive digital platform, wherein the method comprising one or more steps of:
receiving a plurality of data from one or more predefined sources with a prior permission of the user, wherein the plurality of data includes a set of past transactions, and demographic data of the user;
pre-processing the received plurality of data from the one or more sources based on a set of predefined business parameters to receive a filtered data;
analyzing the pre-processed plurality of data with a cognitive digital platform to extract one or more financial information of the user;
collecting a set of training data from the extracted one or more financial information of the user to train a machine learning model;
invoking the trained machine learning model to generate one or more financial business rules using the extracted one or more financial information of the user; and
recommending a credit decision based on the generated one or more financial business rules to lend a loan to the user.

2. The method claimed in claim 1, wherein the user credit profile is used to lend loan amount of small size.

3. The method claimed in claim 1, wherein the one or more sources comprises of one or more online shopping applications, a text of a SMS, and occasion like festival.

4. The method claimed in claim 1, wherein the extracted one or more financial information of the user includes payment for online transactions, account balance update from the personal banking.
5. A system configured to recommend a credit decision based on a cognitive digital platform, wherein the system comprising:
at least one memory storing a plurality of instructions;
one or more hardware processors communicatively coupled with the at least one memory, wherein the one or more hardware processors are configured to execute one or more modules;
a receiving module configured to receive a plurality of data from one or more sources with a prior permission of the user, wherein the plurality of data includes a set of past transactions, and a demographic data of the user;
a pre-processing module configured to pre-processing the received plurality of data from the one or more sources based on a set of predefined business parameters;
an analyzing module configured to analyze the pre-processed plurality of data with an automated cognitive based platform to extract one or more financial information of the user;
a collection module configured to collect a set of training data from the extracted one or more financial information of the user to train a machine learning model;
a invocation module configured to invoke the trained machine learning model to generate one or more financial business rules using the extracted one or more financial information of the user; and
a recommendation module configured to recommend a credit decision based on the generated one or more financial business rules for lending a loan to the user.

6. The system claimed in claim 5, wherein the user credit profile is used to lend loan amount of small size.

7. The system claimed in claim 5, wherein the one or more sources comprises of one or more online shopping applications, a text of a SMS, and occasion like festival.

8. The system claimed in claim 5, wherein the extracting of the one or more financial information of the user includes payment for online transactions, account balance update from the personal banking.

Dated this 27 day of December 2018

Tata Consultancy Limited
By their Agent & Attorney

(Adheesh Nargolkar)
of Khaitan & Co
Reg. No. IN/PA-1086
, Description:TECHNICAL FIELD
[001] The disclosure herein generally relates to a field of an automated credit evaluation and, more particularly, to a system and method for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user.

BACKGROUND
[002] Lending loans in a banking sector is a multi-billion dollar business and there is a lot of focus on the improvement of the business from the operational efficiency point of view using modern approaches like using data analytics. Currently there are plenty of challenges being faced in the industry with respect to scalability and they can be addressed using analytical approaches.

[003] Human subjectivity is a problem in banking domain. Documentation is a challenge in BFSI as banks loose leads. Lot of data points are required for a given loan application for processing a request. The collection of data required for loan decision is a critical job with respect to the time and cost. These data are utilized for analytical model building purposes like score card generations, decision for rejections, acceptance or consider in grey pool cases, estimating probability of default etc. The current business process involves lots of paper submission from customer end and it affects the customer’s ongoing business and therefore it affects the customer satisfaction directly. We may lose the customer leads and it will affect the business. We can get lot of data from APIs from different online authenticated sources and get the data in few seconds of time. The challenge of checking the Type 1 and Type 2 error in day to day decisions in managing the NPA and default rate to a limited value in banking business is also a very critical issue. Furthermore, legality precedes technology. In other words, whatever technology we develop needs to abide by the financial regulation and governance of the particular country. The financial regulations vary from country to country.

SUMMARY
[004] Embodiments of the present disclosure provides technological improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method and system for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user.

[005] A method for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user. The method comprising one or more steps receiving a plurality of data from one or more predefined sources with a prior permission of the user, wherein the plurality of data includes a set of past transactions, and demographic data of the user, pre-processing the received plurality of data from the one or more sources based on a set of predefined business parameters, analyzing the pre-processed plurality of data with an automated cognitive based platform to extract one or more financial information of the user, collecting a set of training data from the pre-processed plurality of data to train a machine learning model, invoking the trained machine learning model to generate one or more financial business rules using the extracted one or more financial information of the user, and recommending a credit decision based on the generated one or more financial business rules to lend a loan to the user.

[006] A system is configured for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user. The system comprising at least one memory storing a plurality of instructions and one or more hardware processors communicatively coupled with the at least one memory. The one or more hardware processors are configured to execute one or more modules comprises of a receiving module, a pre-processing module, an analyzing module, a collection module, an invocation module, and a recommendation module.
[007] The receiving module of the system is configured to receive a plurality of data from one or more sources with a prior permission of the user and a pre-processing module configured to pre-process the received plurality of data from the one or more sources based on a set of predefined business parameters. The pre-processed plurality of data is analyzed at the analyzing module with a cognitive digital platform to extract one or more financial information of the user. Further, the collection module of the system is configured to collect a set of training data from the pre-processed plurality of data to train a machine learning model. The trained machine learning model is invoked to generate one or more financial business rules using the extracted one or more financial information of the user.

[008] 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.

BRIEF DESCRIPTION OF THE DRAWINGS
[009] The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles:

[010] FIG. 1 illustrates a system for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user, according to some embodiments of the present disclosure;

[011] FIG. 2 is a schematic diagram to recommend a credit decision based on a cognitive digital platform, in accordance with some embodiments of the present disclosure; and

[012] FIG. 3 is a flow diagram to illustrate a method for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user, in accordance with some embodiments of the present disclosure.

[013] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems and devices embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, and the like represent various processes which may be substantially represented in computer readable medium and so executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION OF EMBODIMENTS
[014] Exemplary embodiments are described with reference to the accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.

[015] The embodiments herein provide a method and a system for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user. It is to avoid pain at user end by asking him so many documentations as the system can fetch from one or more predefined sources. The system is configured to collect a plurality of data from one or more predefined sources with prior permission of the user. Herein the objective is to construct a system for credit evaluation by employing the machine learning algorithms, so that the people in need of a loan may obtain credit amount faster than those utilizing an existing credit evaluation arrangement without having to reduce the credit evaluation standard. The system comprising at least one memory storing a plurality of instructions and one or more hardware processors communicatively coupled with the at least one memory.

[016] Referring now to the drawings, and more particularly to FIG. 1 through FIG. 3, where similar reference characters denote corresponding features consistently throughout the figures, there are shown preferred embodiments and these embodiments are described in the context of the following exemplary system and/or method.

[017] Referring FIG. 1, wherein the system (100) is configured for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user. The system (100) comprises at least one memory (102) with a plurality of instructions and one or more hardware processors (104) which are communicatively coupled with the at least one memory (102) to execute modules therein.

[018] The hardware processor (104) may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the hardware processor (104) is configured to fetch and execute computer-readable instructions stored in the memory (102). The one or more hardware processors (104) are configured to execute one or more modules comprising a receiving module (106), a pre-processing module (108), an analyzing module (110), a collection module (112), an invocation module (114), and a recommendation module (116).

[019] In the preferred embodiment of the disclosure, a receiving module (106) of the system (100) is configured to receive a plurality of data from one or more predefined sources with a prior permission of the user. The plurality of data includes a set of past transactions from mobile SMS, financial data from credit Bureau and demographic data of the user. Further, the data also comprises Credit Information Bureau of India Limited (CIBIL) score, an average balance, an amount overdue, a delayed payment, an account balance variation, a business type, an industry category etc.

[020] In the preferred embodiment of the disclosure, the pre-processing module (108) of the system (100) is configured to pre-process the received plurality of data from the one or more sources based on a set of predefined business rules. Herein, the predefined business rules include the financial rules derived from the past data of the business. Further, the business rules are derived by applying analytical methods. The business rules include loan acceptance rules, rejection rules and grey loan application rules. Data variables like available balance, past history of transactions, previous loan information, business data like type of business etc. are used for generating the parameters.

[021] In the preferred embodiment of the disclosure, the analyzing module (110) of the system (100) is configured to analyze the pre-processed plurality of data with a cognitive digital platform to extract one or more financial information of the user.

[022] Referring FIG. 2, an example, a schematic diagram to recommend a credit decision based on a cognitive digital platform. It would be appreciated that the cognitive digital platform consists of few layers for processing data. First, the cognitive digital platform shall handle the data pre-processing like data capture from various sources like SMS, APIs data sources, raw data transformation. The financial information can be derived from User’s mobile SMS data, credit bureau records and Bank account details. A natural language processing (NLP) is used to derive the financial data from the SMS. This platform has the ability to capture the data from various sources using the online APIs. The second layer is a cognitive brain of the cognitive digital platform that has all the rules being stored. The third layer consists of the decisions being given to the user. For instance, when a user does any financial transaction using his debit card, he receives an SMS for the same. This SMS data is used to extract the financial information and can be used to create an alternative financial statement of the user.

[023] In the preferred embodiment of the disclosure, the collection module (112) of the system (100) is configured to collect a set of training data from the extracted financial information of the user to train a machine learning model.

[024] In the preferred embodiment of the disclosure, the invocation module (114) of the system (100) is configured to invoke the trained machine learning model to generate one or more financial business rules using the extracted one or more financial information of the user. The one or more financial business rules are generated from the extracted one or more financial information and is essentially used for future customers. These one or more business financial rules are validated using the business data. The one or more business financial rules are in the form of combination of variables.

[025] It would be appreciated that the one or more business financial rules are precisely the rejection rules, acceptance rules and grey loan applications. The acceptance rules allow the loan application to be accepted and give the loan amount and the rejection rules consists of a set of parameters that will reject the loan application. The grey loan application rules are used for negotiating the loan application with the applicant.

[026] In the preferred embodiment of the disclosure, the recommendation module (116) of the system (100) is configured to recommend a credit decision based on the generated one or more financial business rules to lend a loan to the user. It would be appreciated that the recommendation module is configured to make personalized recommendation to each user, when there are many users and a large product catalogue. These recommendations can be in the form of relevant product suggestions, targeted marketing or specific discount strategies.

[027] Referring FIG. 3, a processor-implemented method (200) to for an automated credit evaluation based on a cognitive digital platform to recommend a credit decision for lending a loan to a user. The method comprises one or more steps as follows.

[028] Initially, at the step (202), a plurality of data from one or more predefined sources is received at a receiving module (106) of the system (100) with a prior permission of the user.

[029] In the preferred embodiment of the disclosure, at the next step (204), the received plurality of data from the one or more sources is pre-processed based on a set of predefined parameters at a pre-processing module (108) of the system (100). Herein, the predefined business rules include the financial rules derived from the past data of the business. Further, the business rules are derived by applying analytical methods. The business rules include loan acceptance rules, rejection rules and grey loan application rules.

[030] In the preferred embodiment of the disclosure, at the next step (206), analyzing the pre-processed plurality of data with an automated cognitive based platform at an analyzing module (110) of the system (100) to extract one or more financial information of the user. The financial information can be derived from User’s mobile SMS data, credit bureau records and Bank account details. It would be appreciated that a natural language processing (NLP) is used to derive the financial data from the SMS. This platform has the ability to capture the data from various sources using the online APIs.

[031] In the preferred embodiment of the disclosure, at the next step (208), collecting a set of training data at a collection module (112) of the system (100) from the extracted financial information of the user to train a machine learning model.

[032] In the preferred embodiment of the disclosure, at the next step (210), invoking the trained machine learning model to generate one or more financial business rules using the extracted one or more financial information of the user.

[033] In the preferred embodiment of the disclosure, at the last step (212), a credit decision is recommend at a recommendation module (116) of the system (100) based on the generated one or more financial business rules to lend a loan to the user. It would be appreciated that the recommendation module (116) is configured to make personalized recommendation to each user, when there are many users and a large product catalogue.

[034] The written description describes the subject matter herein to enable any person skilled in the art to make and use the embodiments. The scope of the subject matter embodiments is defined by the claims and may include other modifications that occur to those skilled in the art. Such other modifications are intended to be within the scope of the claims if they have similar elements that do not differ from the literal language of the claims or if they include equivalent elements with insubstantial differences from the literal language of the claims.

[035] The embodiments of present disclosure herein addresses unresolved problem of scalability while lending loans in the banking sector. There is a lot of focus on the improvement of the business from the operational efficiency point of view using modern approaches like using data analytics. Herein, the disclosure provides an automation of the credit evaluation of loan applications in banks using data driven platform based on machine learning algorithms (MLA).

[036] It is to be understood that the scope of the protection is extended to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.

[037] The embodiments herein can comprise hardware and software elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[038] The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that ongoing technological development will change the manner in which particular functions are performed. These examples are presented herein for purposes of illustration, and not limitation. Further, the boundaries of the functional building blocks have been arbitrarily defined herein for the convenience of the description. Alternative boundaries can be defined so long as the specified functions and relationships thereof are appropriately performed. Alternatives (including equivalents, extensions, variations, deviations, etc., of those described herein) will be apparent to persons skilled in the relevant art(s) based on the teachings contained herein. Such alternatives fall within the scope and spirit of the disclosed embodiments. Also, the words “comprising,” “having,” “containing,” and “including,” and other similar forms are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms “a,” “an,” and “the” include plural references unless the context clearly dictates otherwise.

[039] Furthermore, one or more computer-readable storage media may be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processor(s) to perform steps or stages consistent with the embodiments described herein. The term “computer-readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.

[040] It is intended that the disclosure and examples be considered as exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.