WO2022189842A1 - System and method for analyzing financial-behavior of user on digital platforms for assisting financial institution - Google Patents

Abstract

A system for analyzing a financial-behavior of a user on multiple digital platforms for assisting a financial institution is provided. The system includes a data collection module (40) which collects personalized data related to the user from the multiple digital platforms. The system also includes a data management module (50) which segregates the personalized data collected into categories, recognizes a nature of the personalized data segregated, and stores a copy of the nature. The system also includes a financial status identification module (60) which determines a lifestyle and identifies a financial status of the user. The system also includes a collaboration prediction module (70) which predicts a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration, thereby analyzing the financial-behavior of the user on the multiple digital platforms for assisting the financial institution.

Description

SYSTEM AND METHOD FOR ANALYZING FINANCIAL-BEHAVIOR OF USER ON DIGITAL PLATFORMS FOR ASSISTING FINANCIAL

INSTITUTION

EARLIEST PRIORITY DATE: This Application claims priority from a Complete patent application filed in India having Patent Application No. 202121010407, filed on March 12, 2021 and titled “SYSTEM AND METHOD FOR ANALYZING FINANCIAL-BEHAVIOR OF USER ON DIGITAL PLATFORMS FOR ASSISTING FINANCIAL INSTITUTION”. FIELD OF INVENTION

Embodiments of a present invention relate to assisting financial institutions, and more particularly, to a system and method for analyzing a financial-behavior of a user on a plurality of digital platforms for assisting a financial institution.

BACKGROUND Around the world, financial institutions such as banks are making a profit by providing a credit line facility on an aggregator platform for the customers to make the payment for the purchase of the products from one or more sellers on the aggregator platform. However, the profit made by the financial institutions is limited because the financial institutions are unaware of the customer experience, customer’s requirement, customer’s preferences, and the like. There is a plurality of approaches to analyze customer behavior on the aggregator platform and other platforms. However, such a plurality of approaches can analyze the customer behavior related to only a few parameters, thereby making the plurality of approaches less reliable and less efficient.

Hence, there is a need for an improved system and method for analyzing a financial- behavior of a user on a plurality of digital platforms for assisting a financial institution which addresses the aforementioned issues. BRIEF DESCRIPTION

In accordance with one embodiment of the disclosure, a system for analyzing a financial-behavior of a user on a plurality of digital platforms for assisting a financial institution is provided. The system includes one or more processors. The system also includes a data collection module operable by the one or more processors. The data collection module is configured to collect personalized data related to the user from the plurality of digital platforms using a data collection technique. Further, the system also includes a data management module operable by the one or more processors. The data management module is configured to segregate the personalized data collected into one or more categories using artificial intelligence technique. The data management module is also configured to recognize a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique. Further, the data management module is also configured to store a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms after a per- defined time interval. The one or more operations include one of a product purchase, a service order, a monetary transaction, a web search, or a combination thereof. The system also includes a financial status identification module operable by the one or more processors. The financial status identification module is configured to determine a lifestyle of the user upon analyzing the personalized data collected using an image processing technique. Further, the financial status identification module is also configured to identify a financial status of the user using the artificial intelligence technique based on the lifestyle determined. The system also includes a collaboration prediction module operable by the one or more processors. The collaboration prediction module is configured to predict a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial- behavior of the user on the plurality of digital platforms for assisting the financial institution. In accordance with another embodiment, a method for analyzing a financial-behavior of a user on a plurality of digital platforms for assisting a financial institution is provided. The method includes collecting personalized data related to the user from the plurality of digital platforms using a data collection technique. The method also includes segregating the personalized data collected into one or more categories using the artificial intelligence technique. Further, the method also includes recognizing a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique. The method also includes storing a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms after a per- defined time interval, wherein the one or more operations include one of a product purchase, a service order, a monetary transaction, a web search, or a combination thereof. The method also includes determining a lifestyle of the user upon analyzing the personalized data collected using an image processing technique. Further, the method also includes identifying a financial status of the user using the artificial intelligence technique based on the lifestyle determined. The method also includes predicting a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial -behavior of the user on the plurality of digital platforms for assisting the financial institution.

To further clarify the advantages and features of the present disclosure, a more particular description of the disclosure will follow by reference to specific embodiments thereof, which are illustrated in the appended figures. It is to be appreciated that these figures depict only typical embodiments of the disclosure and are therefore not to be considered limiting in scope. The disclosure will be described and explained with additional specificity and detail with the appended figures.

BRIEF DESCRIPTION OF THE DRAWINGS

The disclosure will be described and explained with additional specificity and detail with the accompanying figures in which: FIG. 1 is a block diagram representation of a system for analyzing a financial-behavior of a user on a plurality of digital platforms for assisting a financial institution in accordance with an embodiment of the present disclosure;

FIG. 2 is a block diagram representation of an exemplary embodiment of the system for analyzing the financial-behavior of the user on the plurality of digital platforms for assisting the financial institution of FIG. 1 in accordance with an embodiment of the present disclosure;

FIG. 3 is a block diagram of a financial-behavior analysis computer or financial- behavior analysis a server in accordance with an embodiment of the present disclosure; and

FIG. 4 is a flow chart representing steps involved in a method for analyzing a financial- behavior of a user on a plurality of digital platforms for assisting a financial institution in accordance with an embodiment of the present disclosure.

Further, those skilled in the art will appreciate that elements in the figures are illustrated for simplicity and may not have necessarily been drawn to scale. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the figures by conventional symbols, and the figures may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the figures with details that will be readily apparent to those skilled in the art having the benefit of the description herein.

DETAILED DESCRIPTION

For the purpose of promoting an understanding of the principles of the disclosure, reference will now be made to the embodiment illustrated in the figures and specific language will be used to describe them. It will nevertheless be understood that no limitation of the scope of the disclosure is thereby intended. Such alterations and further modifications in the illustrated system, and such further applications of the principles of the disclosure as would normally occur to those skilled in the art are to be construed as being within the scope of the present disclosure. The terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process or method that comprises a list of steps does not include only those steps but may include other steps not expressly listed or inherent to such a process or method. Similarly, one or more devices or sub-systems or elements or structures or components preceded by "comprises... a" does not, without more constraints, preclude the existence of other devices, sub-systems, elements, structures, components, additional devices, additional sub-systems, additional elements, additional structures or additional components. Appearances of the phrase "in an embodiment", "in another embodiment" and similar language throughout this specification may, but not necessarily do, all refer to the same embodiment.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this disclosure belongs. The system, methods, and examples provided herein are only illustrative and not intended to be limiting.

In the following specification and the claims, reference will be made to a number of terms, which shall be defined to have the following meanings. The singular forms “a”, “an”, and “the” include plural references unless the context clearly dictates otherwise.

Embodiments of the present disclosure relate to a system for analyzing a financial- behavior of a user on a plurality of digital platforms for assisting a financial institution. The financial institution may include banks or Financial Technology-based institutions. The Financial Technology -based institutions may include companies or services that use technology to provide financial services to businesses or consumers. Such financial institutions make a profit by marketing one or more services provided by the financial institution to one or more users either directly or via an aggregator platform. As used herein, the term “aggregator platform” is defined as a platform which purchases one or more products from one or more manufacturers, one or more retailers, or one or more product sellers and make the one or more products available for the one or more users to purchase with additional service or offers to attract the one or more users. So, on such an aggregator platform, the financial institution may provide a credit line facility for the one or more users to make the payment for the one or more products purchased. FIG. 1 is a block diagram representation of a system (10) for analyzing a financial- behavior of a user on a plurality of digital platforms for assisting a financial institution in accordance with an embodiment of the present disclosure. In one embodiment, the user may include one or more clients, one or more customers, startups, companies, and the like. The system (10) includes one or more processors (20). In one embodiment, the plurality of digital platforms may include one of a professional platform, a social platform, a purchase platform, a monetary transaction related platform, an E- commerce platform, a gig economy related platform, and the like, or a combination thereof. The user may be performing one or more operations on the plurality of digital platforms via a user device (30). In one embodiment, the one or more operations may include one of a product purchase, a service order, a monetary transaction, a web search, a job search, applying for jobs, a gig type job search, applying for gig type jobs, and the like, or a combination thereof. In another embodiment, the one or more operations may include one of selling products, providing services, providing job opportunities, and the like. In one exemplary embodiment, the user device (30) may include a mobile phone, a tablet, a laptop, a smartwatch, a smart speaker, one or more Internet of Things (IoT) devices, and the like. As used herein, the term “Internet of Things devices” is defined as devices which are nonstandard computing devices that connect wirelessly to a network and have the ability to transmit data.

In one embodiment, the financial institution may include an institution involved in providing a facility for the user to make a payment on one of the plurality of digital platforms and an aggregator platform when the user performs one of the one or more operations. Further, in one embodiment, assisting the financial institution may include helping the financial institution to increase the profit of the financial institution. Thus, analyzing the financial-behavior of the user may be necessary to assist the financial institution in making a profit.

Further, in order to analyze the financial-behavior of the user, personalized data extracted by the plurality of digital platforms from the user when the user may be performing the one or more operations may have to be analyzed. Thus, the system (10) also includes a data collection module (40) operable by the one or more processors (20). The data collection module (40) is configured to collect the personalized data related to the user from the plurality of digital platforms using a data collection technique. In one embodiment, the personalized data collected may be stored in a database (as shown in FIG. 2) of the system (10). In one embodiment, the database may include a local database or a cloud database. In one embodiment, collecting the personalized data may include collecting the personalized data in one or more forms such as one of a text form, a visual media form, audio form, and the like, or a combination thereof.

Further, in one exemplary embodiment, the personalized data may include one of products purchased related data, monetary transactions related data, user’s social profile related data, user’s professional profile related data, user’s personal interests related data, user’s income related data, or a combination thereof. In one embodiment, the products purchased related data may include one of a product name, a product type, a count of each of one or more products purchased, a cost of each of the one or more products purchased, a type of the aggregator platform used, a retailer’s information, a manufacturer’s information, a product brand information, and the like, or a combination thereof.

Further, in one embodiment, the monetary transactions related data may include one of a financial institution name, transaction amount, an aggregator platform name, details of amount receiving entity, user’s expenditure, and the like, or a combination thereof. In one embodiment, the user’s social profile related data may include one of a user’ s social identifier, a user’ s occupation, a user’ s social profile image, one or more visual media uploaded in the corresponding social platform, one or more social connections of the user, the information related to the purchase made via the social platform, one or more social preferences of the user, and the like, or a combination thereof.

Further, in one embodiment, the user’s professional profile related data may include one of a user’s professional identifier, a user’s occupation, a user’s professional profile image, one or more visual media uploaded in the corresponding professional platform, one or more professional connections of the user, the information related to the purchase made via the professional platform, one or more professional preferences of the user, global achievements, patents, and the like, or a combination thereof. Further, in one embodiment, the user’s personal interests related data may include one of user’s music preferences, user’s food preferences, user’s travel destination preferences, user’s traveling means preferences, a genre of entertainment, user’s product purchase preferences, user’s service preferences, user’s web search preferences, and the like, or a combination thereof. Moreover, in one embodiment, the user’ s income related data may include one of information about one or more user’ s income sources, a count of the one or more user’s income sources, user’s investment related data, and the like, or a combination thereof.

In one exemplary embodiment, the data collection technique may include one of statistical modeling, the artificial intelligence (AI) technique, the machine learning (ML) technique, Internet of Things (IoT), Robotic Process Automation (RPA), or a combination thereof. As used herein, the term “artificial intelligence” refers to the simulation of human intelligence in machines that are programmed to think like humans and mimic their actions.

Further, as used herein, the term “machine learning” is an application of AI that provides systems the ability to automatically learn and improve from experience without being explicitly programmed. Also, as used herein, the term “Internet of Things” refers to a system of interrelated, internet-connected objects that are able to collect and transfer data over a wireless network without human intervention. Further, as used herein, the term “Robotic Process Automation” is defined as a technology which allows people to configure a computing device or a robot to handle repetitive, rule-based digital tasks such as filling in the same information in multiple places, reentering data, copying and pasting, or the like. RPA is a technology with AI capabilities and ML capabilities to handle high-volume, repeatable tasks that previously required humans to perform.

Further, upon receiving the personalized data of the user from the plurality of digital platforms, the personalized data may be segregated to ease the analysis of the corresponding personalized data. Thus, the system (10) also includes a data management module (50) operable by the one or more processors (20). The data management module (50) is operatively coupled to the data collection module (40). The data management module (50) is configured to segregate the personalized data collected into one or more categories using the AI technique. In one embodiment, the data management module (50) may segregate the personalized data collected based on one of the one or more forms of the personalized data, a type of the personalized data, a type of each of the plurality of digital platforms, and the like, or a combination thereof. In one embodiment, the one or more categories may include one or more sub-categories. In one embodiment, the one or more categories may include one of news, music, tourism, movies, shopping, professional moves, achievements, profile images, social moves, professional uploads, social uploads, and the like, or a combination thereof.

Further, the data management module (50) is also configured to recognize a nature of the personalized data segregated under each of the one or more categories using the AI technique. Basically, in one embodiment, the data management module (50) may recognize the nature of the personalized data in the audio form upon analyzing a pattern of the information extracted from the corresponding personalized data to establish statistical correlation. In such embodiment, the pattern of the information may be analyzed upon applying voice recognition through voice biometrics using one of an Automatic Speech Recognition (ASR) technique, a Natural Language Understanding (NLU) technique, or a combination thereof. As used herein, the term “Automatic Speech Recognition technique” is defined as the process of deriving the transcription (word sequence) of an utterance or an audio, given the speech waveform. Basically, the technique is converting speech into text. Further, as used herein, the term “Natural Language Understanding technique” is defined as an artificial intelligence-based technique which is used to extract information from the text or extract meaning of the text, thereby allowing humans to interact with the computers using natural sentences. Moreover, the NLU technique may comprise one or more basics pillars based on which the technique is built, wherein the one or more basics pillars may include identity intent, identity utterness, cover correctness, build exceptions, and the like.

In one embodiment, the nature of the news may include the news being financial news, professional news, social news, audible instructions received by the user device (30) from the user, and the like. In one embodiment, the nature of music may include hard- rock music, soft music, motivational music, relaxing music, and the like. Similarly, in one embodiment, the nature of the personalized data segregated under each of the one or more categories may be recognized by the data management module (50).

Further, the data management module (50) is also configured to store a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms to generate one or more suggestions when the user performs the one or more operations on the plurality of digital platforms after a per- defined time interval.

Further, upon recognizing the nature of the personalized data, a financial status of the user may have to be analyzed using the personalized data collected. Thus, the system (10) also includes a financial status identification module (60) operable by the one or more processors (20). The financial status identification module (60) is operatively coupled to the data management module (50). The financial status identification module (60) is configured to determine a lifestyle of the user upon analyzing the personalized data collected using an image processing technique with deep learning.

In one embodiment, initially, the financial status identification module (60) may generate a training model using the image processing technique with the deep learning upon receiving a plurality of visual media, wherein the training model may be trained to recognize a plurality of well-known brands, a plurality of logos, and the like of companies and startups. In one embodiment, the plurality of visual media received may include the plurality of well-known brands, the plurality of logos, and the like of the companies and the startups. In one embodiment, the training model generated along with the plurality of the visual media received may be stored in the database of the system (10). As used herein, the term “deep learning” is part of a broader family of machine learning methods based on artificial neural networks with representation learning.

Further, the lifestyle of the user may be determined by the financial status identification module (60) based on one of a type of cloths the user has put on in the user’s social profile, the user’s professional profile, the one or more visual media uploaded, a cost of the products purchased, the brands preferred, and the like, or a combination thereof using the training model generated. In one embodiment, the one or more visual media uploaded may include clothing, vehicles, restaurants visited, house locality, places visited across the Globe, and the like. Basically, the financial status identification module (60) may determine the lifestyle of the user upon identifying and analyzing brand logos in the one or more visual media uploaded using the training model generated using the image processing technique with the deep learning. In one exemplary embodiment, the lifestyle may include a low class, a lower- middle-class, an upper middle class, a middle class, an upper class, and the like. As used herein, the term “image processing” is defined as a method to perform some operations on an image, in order to get an enhanced image or to extract some useful information from it.

In addition, in one exemplary embodiment, the financial status identification module (60) may determine the lifestyle of the user upon analyzing the personalized data collected using the training model based on one or more correlations. In one embodiment, the one or more correlations may include one of known faces and known brands correlation, unknown faces and known brands correlation, known faces and unknown brands correlation, unknown face and unknown brands correlation, or a combination thereof. In an embodiment, the known faces and unknown brands correlation may refer to a case where a startup may have hired a known face for branding. In one embodiment, the unknown face and unknown brands correlation may refer to a case comprising one of a startup, a next big thing, a self-branding, and the like. Moreover, the lifestyle determined maybe then compared with the user’s professional profile related data to confirm the one or more correlations based on which the lifestyle is determined. In one exemplary embodiment, the user’s professional profile related data may include a professional reputation of the user, a designation of the user, professional activities of the user, and the like on the professional platform.

Further, the financial status identification module (60) is also configured to identify the financial status of the user using the AI technique based on the lifestyle determined. In one embodiment, the financial status may refer to a wallet size of the user which may decide a spending capability of the user. Basically, the financial status identification module (60) may identify the financial status of the user upon classification and clustering of the personalized data collected which has an indication of the lifestyle maintained by the user. The financial status identification module (60) may initially check for the lifestyle of the user falling under the corresponding one or more correlations. Later, based on the corresponding one or more corresponding correlations if the corresponding lifestyle is maintained by the user, the corresponding financial status of the user may be identified.

Further, once the spending capability of the user is known then, next purchase may be predicted. Thus, in one embodiment, the system (10) also includes a purchase prediction module (as shown in FIG. 2) operable by the one or more processors (20). The purchase prediction module is operatively coupled to the financial status identification module (60). The purchase prediction module is configured to predict a new purchase of a product to be made by the user using the ML technique upon linking the plurality of digital platforms with each other.

Further, the system (10) also includes a collaboration prediction module (70) operable by the one or more processors (20). The collaboration prediction module (70) is operatively coupled to the financial status identification module (60). The collaboration prediction module (70) is configured to predict a financial collaboration to be made by the user with the financial institution via the aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using the ML technique, thereby analyzing the financial-behavior of the user on the plurality of digital platforms for assisting the financial institution.

As used herein, the term “financial collaboration” is defined as a deal made between at least two parties which involve financial transactions based on one or more conditions. Thus, once the financial status of the user is identified, the financial collaboration which the user might make with the one or more clients such as the one or more manufacturers, the one or more retailers, the one or more product sellers, or the like via the aggregator platform can be predicted. Further, in one exemplary embodiment, allotting the rank may include allotting the rank in terms of value, volume, and funding support. As used herein, the term value may refer to the cost of one or more products made available on the aggregator platform by the corresponding one or more clients to be purchased by the user over a pre-defined time period which adds to a revenue of the financial institution upon purchase. The rank in terms of the value may include a low-value collaboration, a moderate value collaboration, and a high-value collaboration. Thus, in one embodiment, when the one or more products made available on the aggregator platform by the one or more clients are expensive, then the rank may include the high-value collaboration. For example, in such embodiment, the revenue made by the financial institution may be about 80 percent (%) to about 90 %. In another embodiment, when the one or more products made available on the aggregator platform by the one or more clients are cheap, then the rank may include the low-value collaboration. For example, in such embodiment, the revenue made by the financial institution may be about 30 % to about 50 %. In yet another embodiment, when the one or more products made available on the aggregator platform by the one or more clients have a moderate cost such as neither too expensive nor too cheap, then the rank may include the moderate value collaboration. For example, in such embodiment, the revenue made by the financial institution may be about 50 % to about 80 %.

Further, as used herein, the term volume may refer to a count of the one or more customers of the one or more clients over the pre-defined time period, wherein the one or more clients have made available the one or more products on the aggregator platform for the one or more customers to purchase, wherein the revenue of the financial institution may be based on the volume. The rank in terms of the volume may include a high volume collaboration, a moderate volume collaboration, and a low volume collaboration. Thus, in one embodiment, when the one or more customers making the purchase of the one or more products put by the corresponding one or more clients on the aggregator platform are in a large quantity irrespective of the cost of the one or more products, then the rank may include the high volume collaboration. In another embodiment, when the one or more customers are in a smaller count, then the rank may include the low volume collaboration. In yet another embodiment, when the one or more customers are in a moderate quantity, then the rank may include the moderate volume collaboration.

Further, as used herein, the term funding support may refer to a case when the user, the one or more customers, or the one or more clients may be interested in funding a start-up, have big ideas, and the like. The rank in terms of the funding support may include funding support collaboration. Again, such a prediction may be made based on the financial status of the user. Moreover, in one embodiment, the collaboration prediction module (70) may generate a statistical model upon performing the statistical analysis on the personalized data using the ML technique. In one exemplary embodiment, the statistical model may capture statistical correlations between client’s product availability customer’ s interest in buying the corresponding one or more products. Subsequently, the collaboration prediction module (70) may calculate a level of confidence about the one or more products being liked by the one or more customers. In addition, in one embodiment, the collaboration prediction module (70) may also generate a pipeline of one or more statistical models generated based on various stages in a lifetime of the user. Thus, the collaboration prediction module (70) may predict the financial collaboration by allotting the rank for the corresponding financial collaboration based on the statistical model generated, the calculation of the confidence, and the pipeline generated using the ML technique. In one exemplary embodiment, the ML technique may include a supervised learning technique, k-nearest neighbors technique, a random forest technique, and the like.

Further, the user performing the one or more operations on the plurality of digital platforms may be a fraudster who is operating a user’s account with a fake social profile or a fake professional profile. Thus, identifying such a fraudster may be important because the fraudster might perform one or more unethical activities via the user’s account. Thus, in one embodiment, the system (10) also includes a fake profile identification module (as shown in FIG. 2) operable by the one or more processors (20). The fake profile identification module may be operatively coupled to the collaboration prediction module (70). The fake profile identification module is configured to identify a fake profile upon comparing the user’s social profile related data with the user’s professional profile related data using the image processing technique with the deep learning. Thus, using the image processing technique with the deep learning might enable the fake profile identification module to identify the fake profile and remember the corresponding fake profile identified for future use.

FIG. 2 is a block diagram representation of an exemplary embodiment of the system (10) for analyzing the financial -behavior of the user on the plurality of digital platforms (80) for assisting the financial institution of FIG. 1 in accordance with an embodiment of the present disclosure. Suppose the financial institution such as a bank ‘X’ (90) has provided a credit line on an aggregator platform Ύ (100) for the user such as a plurality of customers (110) to make a payment for the one or more products which the plurality of customers (110) purchase via the aggregator platform Ύ (100) using a mobile phone (120). As used herein, the term mobile phone (120) is substantially similar to the term user device (30) of FIG. 1. The bank ‘X’ (90) provides one or more offers for the payment to be made for the respective one or more products to be purchased. One or more sellers (125) with brand ‘A’, brand ‘B’, and brand ‘C’ are the one or more sellers (125) whose one or more products are available on the aggregator platform Ύ (100). The bank ‘X’ (90) needs to know the financial-behavior of the plurality of customers (110) not only on the aggregator platform Ύ (100) but also on the plurality of digital platforms (80) described above in the description of FIG. 1. Thus, the bank ‘X’ (90) might use the system (10) to do so. The system (10) includes the one or more processors (20).

Further, the system (10) collects the personalized data related to each of the plurality of customers (110) from the plurality of digital platforms (80) via the data collection module (40) of the system (10) using the data collection technique. Further, along with the browsing data and the purchase related data, the personalized data may also include the information shared over the one or more IoT devices (150) such as the smartwatch, smart speaker, and the like. Later, the personalized data collected is segregated and the nature of the personalized data is recognized via the data management module (50) of the system (10) using the AI technique. The personalized data collected and segregated is stored in the database (160) of the system (10).

Further, the data management module (50) via the web crawling stores the nature in the database (160) to generate the one or more suggestions when the corresponding plurality of customers (110) performs the one or more operations on the plurality of platforms (80) at the later stage. Later, upon applying the image processing technique on the personalized data of the corresponding plurality of customers (110), the lifestyle can be determined by the financial status identification module (60) of the system (10), thereby identifying the financial status of each of the plurality of customers (110) using the AI technique.

Further, upon identifying the financial status, the next purchase which the corresponding plurality of customers (110) might make can be identified by the purchase prediction module (170) of the system (10) using the ML technique upon linking the plurality of digital platforms (80) with each other. Later, the financial status can also be used to predict the financial collaboration which the corresponding plurality of customers (110) might make with at least one of the one or more sellers (125) via the aggregator platform Ύ (100) by the collaboration prediction module (70) of the system (10) by allotting the rank to financial collaboration predicted using the ML technique.

Suppose a customer ‘W’ of the plurality of customers (110) purchases one or more products of the brand ‘A’ and the brand ‘B’ which are expensive brands, then when the bank ‘X’ (90) uses the system (10), the collaboration prediction module (70) predicts the next financial collaboration which the customer ‘W’ can make by allotting the rank including a high-value collaboration as the brand ‘A’ and the brand ‘B’ are the expensive brands.

Further, there could be multiple accounts with the same name of which except one account rest accounts are the accounts created by fraudsters. Thus, it becomes important to keep a track of fake profiles. Thus, the system (10) identifies the fake profile upon applying the image processing technique on the personalized data obtained with deep learning via the fake profile identification module (180) of the system (10).

FIG. 3 is a block diagram of a financial-behavior analysis computer or a financial- behavior analysis server (190) in accordance with an embodiment of the present disclosure. The financial-behavior analysis server (190) includes processor(s) (200), and a memory (210) coupled to a bus (220). As used herein, the processor(s) (200) and the memory (210) are substantially similar to the system (10) of FIG. 1. Here, the memory (210) is located in a local storage device.

The processor(s) (200), as used herein, means any type of computational circuit, such as, but not limited to, a microprocessor, a microcontroller, a complex instruction set computing microprocessor, a reduced instruction set computing microprocessor, a very long instruction word microprocessor, an explicitly parallel instruction computing microprocessor, a digital signal processor, or any other type of processing circuit, or a combination thereof. Computer memory elements may include any suitable memory device(s) for storing data and executable program, such as read only memory, random access memory, erasable programmable read only memory, electrically erasable programmable read only memory, hard drive, removable media drive for handling memory cards and the like. Embodiments of the present subject matter may be implemented in conjunction with program modules, including functions, procedures, data structures, and application programs, for performing tasks, or defining abstract data types or low-level hardware contexts. Executable program stored on any of the above-mentioned storage media may be executable by the processor(s) (200).

The memory (210) includes a plurality of modules stored in the form of executable program which instructs the processor(s) (200) to perform method steps illustrated in FIG. 3. The memory (210) has following modules: a data collection module (40), a data management module (50), a financial status identification module (60), and a collaboration prediction module (70).

The data collection module (40) is configured to collect personalized data related to the user from the plurality of digital platforms (80) using a data collection technique. The data management module (50) is configured to segregate the personalized data collected into one or more categories using artificial intelligence technique. The data management module (50) is also configured to recognize a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique.

The data management module (50) is configured to store a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms (80) to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms (80) after a per-defined time interval, wherein the one or more operations include one of a product purchase, a service order, a monetary transaction, a web search, a job search, applying for jobs, a gig type job search, applying for gig type jobs, or a combination thereof.

The financial status identification module (60) is configured to determine a lifestyle of the user upon analyzing the personalized data collected using an image processing technique with deep learning. The financial status identification module (60) is also configured to identify a financial status of the user using the artificial intelligence technique based on the lifestyle determined.

The collaboration prediction module (70) is configured to predict a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial-behavior of the user on the plurality of digital platforms (80) for assisting the financial institution.

FIG. 4 is a flow chart representing steps involved in a method (230) for analyzing a financial-behavior of a user on a plurality of digital platforms for assisting a financial institution in accordance with an embodiment of the present disclosure. The method (230) includes collecting personalized data related to the user from the plurality of digital platforms using a data collection technique in step 240. In one embodiment, collecting the personalized data related to the user from the plurality of digital platforms includes collecting the personalized data related to the user from the plurality of digital platforms by a data collection module (40). In one exemplary embodiment, collecting the data includes collecting the data in one or more forms such as one of a text form, a visual media form, an audio form, and the like, or a combination thereof.

The method (230) also includes segregating the personalized data collected into one or more categories using artificial intelligence technique in step 250. In one embodiment, segregating the personalized data collected into the one or more categories includes segregating the personalized data collected into the one or more categories by a data management module (50).

Furthermore, the method (230) includes recognizing a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique in step 260. In one embodiment, recognizing the nature of the personalized data segregated under each of the one or more categories includes recognizing the nature of the personalized data segregated under each of the one or more categories by the data management module (50). Furthermore, the method (230) includes storing a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms after a per-defined time interval, wherein the one or more operations include one of a product purchase, a service order, a monetary transaction, a web search, a job search, applying for jobs, a gig type job search, applying for gig type jobs, or a combination thereof in step 270. In one embodiment, storing the copy of the nature of the personalized data includes storing a copy of the nature of the personalized data by the data management module (50).

Furthermore, the method (230) also includes determining a lifestyle of the user upon analyzing the personalized data collected using an image processing technique with deep learning in step 280. In one embodiment, determining the lifestyle of the user includes determining the lifestyle of the user by a financial status identification module (60).

Furthermore, the method (230) also includes identifying a financial status of the user using the artificial intelligence technique based on the lifestyle determined in step 290. In one embodiment, identifying the financial status of the user includes identifying the financial status of the user by the financial status identification module (60).

Furthermore, the method (230) also includes predicting a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial-behavior of the user on the plurality of digital platforms for assisting the financial institution in step 300. In one embodiment, predicting the financial collaboration to be made by the user with the financial institution includes predicting the financial collaboration to be made by the user with the financial institution by a collaboration prediction module (70).

Further, from a technical effect point of view, the implementation time required to perform the method steps included in the present disclosure by the one or more processors (20) of the system is very minimal, thereby the system maintains very minimal operational speed.

Various embodiments of the present disclosure enable the financial institutions to analyze the financial-behavior of the user on the plurality of digital platforms which enables prediction of future collaborations which the user might make, thereby increasing the customer base and hence the profit of the financial institutions. Further, the system enables analyzing almost all the parameters related to the financial- behavior of the user which also includes identifying the wallet size of the user, thereby making the system more reliable and more efficient. Furthermore, a provision provided by the system to collect the personalized data also from the gig economy related platform helps in identifying credit scores, thus eliminating Credit Bureau Layer, thereby making the system more efficient.

While specific language has been used to describe the disclosure, any limitations arising on account of the same are not intended. As would be apparent to a person skilled in the art, various working modifications may be made to the method in order to implement the inventive concept as taught herein.

The figures and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, order of processes described herein may be changed and are not limited to the manner described herein. Moreover, the actions of any flow diagram need not be implemented in the order shown; nor do all of the acts need to be necessarily performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts. The scope of embodiments is by no means limited by these specific examples.

Claims

I/WE CLAIM:

1. A system (10) for analyzing a financial-behavior of a user on a plurality of digital platforms (80) for assisting a financial institution, wherein the system (10) comprises: one or more processors (20); a data collection module (40) operable by the one or more processors (20), wherein the data collection module (40) is configured to collect personalized data related to the user from the plurality of digital platforms (80) using a data collection technique; a data management module (50) operable by the one or more processors (20), wherein the data management module (50) is configured to: segregate the personalized data collected into one or more categories using the artificial intelligence technique; recognize a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique; and store a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms (80) to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms (80) after a per-defined time interval, wherein the one or more operations comprise one of a product purchase, a service order, a monetary transaction, a web search, a job search, applying for jobs, a gig type job search, applying for gig type jobs, or a combination thereof; a financial status identification module (60) operable by the one or more processors (20), wherein the financial status identification module (60) is configured to: determine a lifestyle of the user upon analyzing the personalized data collected using an image processing technique with deep learning; and identify a financial status of the user using the artificial intelligence technique based on the lifestyle determined; and a collaboration prediction module (70) operable by the one or more processors (20), wherein the collaboration prediction module (70) is configured to predict a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial-behavior of the user on the plurality of digital platforms (80) for assisting the financial institution.

2. The system (10) as claimed in claim 1, wherein collecting the personalized data comprises collecting the personalized data in one or more forms such as one of a text form, a visual media form, an audio form, or a combination thereof.

3. The system (10) as claimed in claim 1, wherein the personalized data comprises one of products purchased related data, monetary transactions related data, user’s social profile related data, user’s professional profile related data, user’s personal interests related data, user’s income related data, or a combination thereof.

4. The system (10) as claimed in claim 1, wherein the plurality of digital platforms (80) comprises one of a professional platform, a social platform, a purchase platform, a monetary transaction related platform, an E-commerce platform, a gig economy related platform, or a combination thereof.

5. The system (10) as claimed in claim 1, wherein the data collection technique comprises one of statistical modeling, the artificial intelligence technique, the machine learning technique, Internet of Things, Robotic Process Automation, or a combination thereof.

6. The system (10) as claimed in claim 1, wherein allotting the rank comprises allotting the rank in terms of value, volume, and funding support.

7. The system (10) as claimed in claim 1, comprises a purchase prediction module (170) operable by the one or more processors (20), wherein the purchase prediction module (170) is configured to predict a new purchase of a product to be made by the user using the machine learning technique upon linking the plurality of digital platforms (80) with each other.

8. The system (10) as claimed in claim 1, comprises a fake profile identification module (180) operable by the one or more processors (20), wherein the fake profile identification module (180) is configured to identify a fake profile upon comparing the user’s social profile related data with the user’s professional profile related data using the image processing technique with deep learning.

9. A method (230) for analyzing a financial-behavior of a user on a plurality of digital platforms for benefiting a financial institution, wherein the method (230) comprises: collecting, by a data collection module (40), personalized data related to the user from the plurality of digital platforms using a data collection technique; (240) segregating, by a data management module (50), the personalized data collected into one or more categories using the artificial intelligence technique; (250) recognizing, by the data management module (50), a nature of the personalized data segregated under each of the one or more categories using the artificial intelligence technique; (260) storing, by the data management module (50), a copy of the nature of the personalized data recognized upon performing web crawling on each of the plurality of digital platforms to generate one or more suggestions when the user performs one or more operations on the plurality of digital platforms after a per- defined time interval, wherein the one or more operations comprise one of a product purchase, a service order, a monetary transaction, a web search, a job search, applying for jobs, a gig type job search, applying for gig type jobs, or a combination thereof; (270) determining, by a financial status identification module (60), a lifestyle of the user upon analyzing the personalized data collected using an image processing technique with deep learning; (280) identifying, by the financial status identification module (60), a financial status of the user using the artificial intelligence technique based on the lifestyle determined; and (290) predicting, by a collaboration prediction module (70), a financial collaboration to be made by the user with the financial institution via an aggregator platform by allotting a rank for the corresponding financial collaboration upon performing statistical analysis on the personalized data using a machine learning technique, thereby analyzing the financial-behavior of the user on the plurality of digital platforms for assisting the financial institution (300).

10. The method (230) as claimed in claim 9, wherein collecting the data comprises collecting the data in one or more forms such as one of a text form, a visual media form, an audio form, or a combination thereof.