PRIORITY INFORMATION

[001] The present application claims priority from Indian application no. 202221049349 filed on 30 ^th August, 2022.

TECHNICAL FIELD

[002] The present subject matter described herein, in general, relates to a system and a method for resource allocation in real time on a platform.

BACKGROUND

[003] Generally, a decision-making ability and financial awareness are important factors affecting the course of an individual’s life. Conventionally, the decision-making abilities are known to be affected when the personal interests influence the decisions. Traditionally decision making in terms of financial decisions have been instinctive, biased, influenced, and uninformed. Typically, financial planning choices are influenced by marketers, banking professionals, chartered accountants and similar professionals.

[004] Financial decisions often prove to be life changing because of the direct and often irreversible consequences. Conventional approaches for decision making lack clarity, structure, and a practical thought process. Typically, financial decision making has been a personal choice dependent only on limited factors such as a person’s income, location, and materialistic estate.

[005] There is a requirement for a holistic and practical decision-making in all walks, including the financial decisions. Lack of a holistic approach results in inaccurate, and inadequate understanding of an individual's requirements. Consequently, the individual’s decision making is affected and a moderately or a negligibly benefitting financial decision is made by the individual. Therefore, there is a requirement for an unbiased, reasonable, customizable, and reliable solution to take informed and justifiable decisions.

SUMMARY

[006] Before the present system(s) and method(s), are described, it is to be understood that this application is not limited to the particular system(s), and methodologies described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosures. It is also to be understood that the terminology used in the description is for the purpose of describing the particular implementations or versions or embodiments only and is not intended to limit the scope of the present application. This summary is provided to introduce aspects related to a system and a method for resource allocation in real time on an interface. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.

[007] In one implementation, a method implemented by a system for resource allocation in real time on an interface is disclosed. Initially, a request for resource allocation may be received through a selection of a user control on an interface of a system. Further, a set of questions may be rendered on the interface. The set of questions may be understood to be related to a set of facets. Subsequently, a set of answers may be received on the interface in response to the set of questions. Further, the set of answers may be scored to generate a user score for each of the set of answers. Each of the set of answers may be understood to correspond to each of the set of facets. Further, a money sign from a set of money signs may be assigned to the user based on the user score and the set of answers. Furthermore, a profile data of the user may be automatically extracted. The profile data may comprise a financial status, and a transaction history. Subsequently, a user profile may be created comprising the money sign, a generation identifier (ID) and the profile data. The user profile may be understood to be unique to the user. Subsequently, an ideal recommendation may be determined for the user for the set of metrics based on the generation ID using a machine learning model. Further, the ideal recommendation may be modified for the set of metrics based on the money sign using deep learning algorithms. The modification may be understood to be within a minimum and a maximum threshold of the ideal recommendation. In next step, a financial score for the user may be determined for each of the set of metrics based on the profile data of the user. Subsequently, a deviation score of the user from the ideal recommendation may be computed for the user upon modification for each of the set of metrics. Further, a net score may be calculated for the user based on the financial score. The net score may be understood to be calculated based on more than one financial score. Finally, a resource allocation may be recommended to the user based upon the net score, and the ideal recommendation.

[008] In another implementation, a non-transitory computer readable medium embodying a program executable in a computing device for resource allocation is disclosed. The program may comprise a program code for receiving a request for resource allocation through a selection of a user control on an interface of a system. Further, the program may comprise a program code for rendering a set of questions on the interface. The set of questions may be understood to be related to a set of facets. Furthermore, the program may comprise a program code for receiving a set of answers on the interface in response to the set of questions. Subsequently, the program may comprise a program code for scoring the set of answers to generate a user score for each of the set of answers. Each of the set of answers may be understood to correspond to each of the set of facets. Further, the program may comprise a program code for assigning a money sign from a set of money signs to the user based on the user score and the set of answers. Further, the program may comprise a program code for automatically extracting a profile data of the user. The profile data may be understood to comprise a financial status, and a transaction history. Furthermore, the program may comprise a program code for creating a user profile comprising the money sign, a generation identifier (ID), and the profile data. The user profile may be understood to be unique to the user. Subsequently, the program may comprise a program code for determining an ideal recommendation for the user for a set of metrics based on the generation ID using a machine learning model. Subsequently, the program may comprise a program code for modifying the ideal recommendation for the set of metrics based on the money sign using deep learning algorithms. The modification may be within a minimum threshold and a maximum threshold of the ideal recommendation. Further, the program may comprise a program code for determining a financial score for the user for each of the set of metrics based on the profile data of the user. Subsequently, the program may comprise a program code for computing a deviation score of the user by comparing the financial score with the ideal recommendation upon modification for each of the set of metrics. Further, the program may comprise a program code for calculating a net score for the user based on more than one financial score. Finally, the program code may comprise a program for recommending a resource allocation to the user based upon the net score and the ideal recommendation.

BRIEF DESCRIPTION OF THE DRAWINGS

[009] The foregoing detailed description of embodiments is better understood when read in conjunction with the appended drawings. For the purpose of illustrating of the present subject matter, an example of a construction of the present subject matter is provided as figures, however, the invention is not limited to the specific method and system for resource allocation in real time on an interface disclosed in the document and the figures. [010] The present subject matter is described in detail with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to refer to various features of the present subject matter.

[Oil] Figure 1 illustrates a network implementation for resource allocation to a user in real time on an interface, in accordance with an embodiment of the present subject matter.

[012] Figure 2 illustrates a method for resource allocation to a user in real time on an interface, in accordance with an embodiment of the present subject matter.

[013] Figure 3 illustrates an exemplary view of an embedding space in accordance with the present invention.

[014] Figure 4 illustrates an exemplary artificial neural network in accordance with the present invention.

[015] The figure depicts an embodiment of the present disclosure for purposes of illustration only. One skilled in the art will readily recognize from the following discussion that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.

DETAILED DESCRIPTION

[016] Some embodiments of this disclosure, illustrating all its features, will now be discussed in detail. The words "receiving," "extracting," "rendering," "assigning," and other forms thereof, are intended to 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. Although any system and methods similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary, system and methods are now described.

[017] The disclosed embodiments are merely examples of the disclosure, which may be embodied in various forms. Various modifications to the embodiment will be readily apparent to those skilled in the art and the generic principles herein may be applied to other embodiments. However, one of ordinary skill in the art will readily recognize that the present disclosure is not intended to be limited to the embodiments described but is to be accorded the widest scope consistent with the principles and features described herein. [018] The present subject matter discloses a method and a system for resource allocation to a user in real time through an online resource allocation platform. The term “resource allocation” as used herein refers to a financial plan, investment advisory or a financial guidance provided to the user in real time through an online system providing automated resource planning services. The aim of the invention is to automatically analyse a person’s personality and psychological preferences, a financial condition, an investment history and recommend appropriate resource allocation to the user without human intervention. The resource allocation is tailored according to the user’s age, a profile data, a money sign, an ideal recommendation, and a net score calculated for the user. The term “money sign” as used herein refers to a symbolic representation of a unique set of personality traits and attributes. Each of the set of predefined money signs is devised based upon a unique psychological profile, and financial personality. In other words, each money sign represents one particular psychological profile and financial personality.

[019] The method is implemented on an automated resource allocation system having a server, a communication network, processor and a user interface. The system may be understood as a digital platform i.e., a software -based online infrastructure that facilitates interactions and transactions between a service provider and a user. The user interface provides user selectable controls to facilitate interaction of the user with the system. In an aspect, the system employs a set of computer-executable- instructions to conduct an on-line chat conversation via text or text-to- speech, in lieu of providing direct contact with a live human agent. For example, the computer-executable- instructions are configured to provide automated resource allocation services by automating conversations, extracting user data, and performing robust Al based analysis on the extracted data.

[020] In an embodiment, the system receives a request for resource allocation for a user on the interface of the system. It may be understood that the request may be received through a selection of a user control on the interface. Further, the system renders a set of questions on the interface for the user to answer. The set of questions is each mapped to a set of facets and are used to detect whether the user has a certain facet or not based on the answer received from the user. The term “facet” as used herein refers to a personality characteristic such as curiosity. In one example, the set of facets may comprise creativity, patience, organization, discipline, hyper competition, aggressiveness, satisfaction, and anxiety.

[021] Furthermore, the system receives a set of answers from the user on the interface. Upon receiving the answers, the system assigns a money sign from a set of money signs to the user based on the set of answers. Further, each of the set of answers may be scored using a scoring matrix and deep learning algorithms. Furthermore, each answer of the user may be provided a user score.

[022] Further, the system 102 automatically extracts a profile data of the user, creates a user profile, determines an ideal recommendation using a machine learning model, modifies the ideal recommendation within a minimum threshold and a maximum threshold, determines a financial score for the user, computes a deviation score for the user, calculates a net score for the user based on more than one financial score, and recommends a resource allocation to the user.

[023] To elaborate further, a user profile may be referred to as an individual record of the user comprising all details related to the user as may be available to the system. In one example, the user profile may comprise an identity proof, a date of birth, an address, an email address, a money sign assigned to the user, and a profile data. The profile data may be understood to comprise a financial status of the user and a transaction history. It may be understood that the user profile may be specific to the user. Further, the user profile may be updated on a regular time interval for staying relevant. In one example, the system 102 may protect the profile data of the user for security purposes.

[024] Further, a generation identifier (ID) may be referred to as a generation to which the user belongs in a family. If the user has parents who are employed as well, the parents would be referred to as a first-generation earner, and the generation ID for the parents of the user will be “Gl” or“l”. Similarly, since the user belongs to generation 2 of earners within the family, after the parents of the user, the generation ID for the user will be “G2” or “2”. In other example, if the parents of the user have retired, the user would become a first-generation earner of the family. The generation ID for the user will be “Gl” or “1”.

[025] Further, a reference matrix may be referred to as an illustrative representation comprising at least the set of metrics, the user scores, the ideal recommendation, the minimum threshold, the maximum threshold, and the deviation. The reference matrix may be created to provide the illustration of the various parameters involved in the resource allocation.

[026] Furthermore, an ideal recommendation may be referred to as a percentage allocation for each of the set of metrics for the user. The ideal recommendation may be based on the generational identifier (ID) and the user score. In one example, the ideal recommendation may be provided in the percentage. The system 102 may determine a minimum threshold and a maximum threshold for the ideal recommendation. Further, a minimum threshold and a maximum threshold of the ideal recommendation may be understood as a minimum value and a maximum value of the ideal recommendation that must be followed for the user. [027] Furthermore, a deviation score of the user may be referred to as a difference between the ideal recommendation and the user’s current financial status for each of the set metrics.

[028] Further, a net score of the user may be referred to as an average of more than one financial score calculated for the set of metrics for the user. In other words, the net score may be considered as an average of the financial scores determined by the system 102 for the user. [029] Finally, the resource allocation may be referred to as a financial plan or a financial guidance for the user. The resource allocation may comprise the ideal recommendation as modified for the user within the minimum threshold and the maximum threshold for each of the set of metrics. In other words, the resource allocation may guide the user to act and improve the net score.

[030] Certain technical challenges exist for achieving the goal of recommending resource allocation to a user in real time on an interface. One technical challenge includes automatically and accurately determining an ideal recommendation for the user based on the scoring of each of the set of facets in the reference matrix, and the generation identifier (ID). The ideal recommendation may be understood to be based upon a set of metrics. The solution presented by the embodiments disclosed herein to address the above challenge is a machine learning model for Natural Language Processing (NLP) techniques. It may be noted that use of one or more machine learning models is required to select the ideal recommendation for the user. The machine learning model may comprise a Term Frequency - Inverse Document Frequency (TF- IDF), a Support Vector Machine (SVM), a regression model, and a convolutional neural network (CNN).

[031] Another technical challenge includes automatically defining and modifying a minimum threshold and a maximum threshold for the ideal recommendation based on the money sign. The term modified may be understood as changing, and customizing the ideal recommendation for the user, based on the user score for each of the set of facets. For example, the ideal recommendation for a user may be 70% but the system 102 may adapt the ideal recommendation to 65% after considering the set of metrics, the user’s money sign and a set of financial goals as conveyed by the user. The system may analyse the user profile and accordingly adapt the ideal recommendation to suit the user in a most appropriate way. The solution presented by the embodiments disclosed in the present invention include use of deep learning algorithms to understand the user’s age, financial condition and accordingly define a minimum threshold and a maximum threshold for the ideal recommendation and adapt the ideal recommendation for the user. [032] Referring now to Figure 1, a network implementation 100 of a system 102 for recommending a resource allocation to a user in real time on an interface is disclosed. Initially, the system 102 receives a request for resource allocation through a selection of a user control on an interface of the system. In an example, the software may be installed on a user device 104-1. It may be noted that the one or more users may access the system 102 through one or more user devices 104-2, 104-3... 104-N, collectively referred to as user devices 104, hereinafter, or applications residing on the user devices 104. The system 102 receives the request from a user from one or more user devices 104. Further, the system may also 102 receive from a user using the user devices 104.

[033] Although the present disclosure is explained considering that the system 102 is implemented on a server, it may be understood that the system 102 may be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a virtual environment, a mainframe computer, a server, a network server, a cloudbased computing environment. It will be understood that the system 102 may be accessed by multiple users through one or more user devices 104-1, 104-2. . . 104-N.

[034] In one implementation, the system 102 may comprise the cloud-based computing environment in which the user may operate individual computing systems configured to execute remotely located applications. Examples of the user devices 104 may include, but are not limited to, a portable computer, a personal digital assistant, a handheld device, and a workstation. The user devices 104 are communicatively coupled to the system 102 through a network 106.

[035] In one implementation, the network 106 may be a wireless network, a wired network, or a combination thereof. The network 106 can be implemented as one of the different types of networks, such as intranet, local area network (LAN), wide area network (WAN), the internet, and the like. The network 106 may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further the network 106 may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.

[036] In one embodiment, the system 102 may include at least one processor 108, an input/output (I/O) interface 110, and a memory 112. The at least one processor 108 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, Central Processing Units (CPUs), state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the at least one processor 108 is configured to fetch and execute computer-readable instructions stored in the memory 112.

[037] The I/O interface 110 may include a variety of software and hardware interfaces, for example, a web interface, a graphical user interface, and the like. The I/O interface 110 may allow the system 102 to interact with the user directly or through the client devices 104. Further, the VO interface 110 may enable the system 102 to communicate with other computing devices, such as web servers and external data servers (not shown). The VO interface 110 can facilitate multiple communications within a wide variety of networks and protocol types, including wired networks, for example, LAN, cable, etc., and wireless networks, such as WLAN, cellular, or satellite. The I/O interface 110 may include one or more ports for connecting a number of devices to one another or to another server.

[038] The memory 112 may include any computer-readable medium or computer program product known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and/or non-volatile memory, such as read only memory (ROM), erasable programmable ROM, flash memories, hard disks, Solid State Disks (SSD), optical disks, and magnetic tapes. The memory 112 may include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types. The memory 112 may include programs or coded instructions that supplement applications and functions of the system 102. In one embodiment, the memory 112, amongst other things, serves as a repository for storing data processed, received, and generated by one or more of the programs or the coded instructions.

[039] As there are various challenges observed in the existing art, the challenges necessitate the need to build the system 102 for automatically recommending a resource allocation to a user in real time on an interface. At first, a user may use the user device 104 to access the system 102 via the I/O interface 110. The user may register the user devices 104 using the I/O interface 110 in order to use the system 102. In one aspect, the user may access the I/O interface 110 of the system 102. The detailed functioning of the system 102 is described below with the help of figures.

[040] The present subject matter describes the system 102 for recommending a resource allocation to a user in real time on an interface. Initially, the system 102 may receive a request for resource allocation through a selection of a user control on an interface of a system. In response to receiving the request for resource allocation, the system may render a form on the interface for the user to fill. The form may comprise fillable fields for receiving demographic information pertaining to the user. The demographic information may include but is not limited to a name of the user, an identity proof of the user, a username, an email address of the user, a location of the user, a date of birth and a contact number of the user. In one example, the user may use a desktop to access the interface of the system 102. In another example, the user may use a mobile device to access the interface of the system 102. It may be understood that the user may use multiple devices for accessing the interface.

[041] In an embodiment, the system may generate a customized set of questions based on the demographic information provided by the user. For example, the demographic information may indicate an age and ethnicity of the user. The system generates a set of questions customized according to the age range of the user. The set of questions may be selected set of scenariobased questions where the scenarios are pertinent to the age and ethnicity and culture of the user as can be inferred from the demographic information. In one example, the user may be a student finishing higher education and in search for a job opportunity. In another example, the user may be a retired serviceman saving for his post retirement life. In yet another example, the user may be a sole bread earner of the family exploring financial investment options.

[042] Upon receiving the request to recommend a resource allocation for the user, the system 102 may render a set of questions on the interface for the user to answer. It may be understood that the set of questions may be related to a set of facets relating to a psychological profile and a financial personality of the user. In one example, the set of questions may comprise descriptive questions. In another example, the set of questions may comprise multiple choicebased questions providing the user a choice to select any one option out of a set of four options as the answer. In yet another example, the set of questions may be scenario-based questions requiring the user to imagine a financial situation, and provide an answer to the question.

[043] Further, the “facet” of the set of facets may be understood as a psychological, and a behavioural quality of the user. It may be understood that the facets denote a behavioural trait of the user. For instance, a positive attitude is a facet of a user and the behavioural trait denoted by the positive attitude is optimism. In another instance, a negativity of thoughts and depression are facets of the user with a nervous behavioural trait. Table 1 below enlists the set of facets considered predominantly before the resource allocation by the system 102:

Table 1

[044] Further, in one embodiment each of the set of facets may be scored as: a higher level, a lower level, and a neutral level. For example, a highly curious user may belong to the higher level for ‘curiosity’ facet. In another example, each of the set of facets may be scored on a scale of 1 to 5 with 1 as a minimum limit and 5 as a maximum limit.

[045] In one example, the system 102 may also perform a generational analysis based on age and profession to identify the generation identifier (ID) to which the user may belong to. For example, if the user is a physical labourer of 45 years of age, the user may be the only one earning for the entire family. In other words, the user may belong to Generation 1 or G1 of the family earning for the family. In another example, if a user is a skilled professional of 24 years of age, one or both parent of the user may be retired from their service. Therefore, the skilled professional may be considered to belong to a Generation 2 or G2 of the family as the parents of the user may be considered to belong to a Generation 1 or G1 of the family earning money for the family as the parents of the user may be receiving a monthly pension, or a fixed amount depending on the amount of savings post retirement. Therefore, the generation ID may help understand the generation of earners within a family unit to which the user belongs.

[046] In yet another example, a user may be a grandchild of a successful businessman.

Further, the businessman may be considered to belong to a Generation 1 of the family earners. Furthermore, a son of the business may be considered to belong to a Generation 2 of the family earners. Further, the user may be considered to belong to a Generation 3 after the businessman (Generation 1) and the user’s parents (Generation 2). Therefore, the generational analysis based on age and profession may help identify if the user belongs to a Generation 1, a Generation 2, or a Generation 3 of the user’s family. It may be understood that the generational analysis may impact a plurality of factors including but not limited to a financial risk-taking ability, a preference in investments, and an emergency planning for the user. The emergency planning may be understood to include a liquidity-to-expense ratio, a health insurance, and a life insurance-to-income ratio for a user. Therefore, the emergency planning may be understood to involve the set of metrics that play an important role in any case of emergency for the user such as the health insurance, the life insurance to income ratio.

[047] Further, the system 102 may receive a set of answers from the user. The set of answers may be received on the interface. It may be understood that the set of answer may be received from the user in an audio format, a textual format, an image format, and a video format. Further, if the set of answer is received in the audio format, the image format and the video format the set of answer may be converted to a structured data format. In one example, the system 102 may score each of the set of answers based on a scoring matrix, and deep learning algorithms to assign a user score to each answer of the set of answers. Examples of the deep learning algorithms include Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Artificial Neural Networks (ANN). It may be understood that the deep learning algorithms may include a dataset of questions, a dataset of answers, and a collection of key components for the dataset of answers. Further, the data set of questions may comprise questions for different topics, subtopics, subjects related to user behaviour and preferences applicable for any user on the interface. The probable set of answers for each of the question in the data set may be first determined by the deep learning algorithm and verified manually prior to the training phase. Furthermore, a new answer received from the user may be added to the dataset of answers. Similarly, a scoring matrix, and a corresponding dataset of user scores, for the set of answers may be maintained. The system 102 may calculate the user score for the new answer based on the deep learning algorithms, and the assign user scores for each of answer in the data set of answers.

[048] Further, the system 102 may calculate a user score for each of the facet for each money sign in the set of money signs. It may be noted that each money sign may be devised based on a facet score for each of the set of facets for all money signs. In other words, the facet score for each facet in each money sign is fixed, predetermined, and distinct from rest of the money signs. Therefore, the user score may be matched to the facet score of each money sign to understand which money sign the user belongs to. The matching money sign may have facet scores close to or identical to the user scores for each of the facets. The scoring matrix may calculate the user score for each of the facets, each of the money signs and compare accordingly. It may be understood that the money sign with a maximum match is assigned to the user. In one example, the system 102 may comprise a set of 08 money signs. In another example, the system 102 may comprise a set of 10 money signs. It may be understood that the system 102 may comprise more than one money sign at any given time in the set of money signs. In another example, the set of money signs may be analogous to a set of psychological profiles. In yet another example, the set of money signs may be analogous to a set of personality types. It may be pertinent to note that each of the money sign of the set of money sign is distinctive from every other money sign of the set of money sign. In other words, no two money signs of the set of money sign may be identical at any given point of time.

[049] For example, an answer received from the user on a question related to curiosity, may be first scored by the system 102 on a scale of 1 to 5. The answer may determine how curious the user is starting with a minimum of score 1 to a maximum of score 5. In one example, the system 102 may use natural language processing to understand the set of answers provided by the user. In other example, the question may be “What is your pattern for asset class purchases in the last 5 years?” and the user may be given a set of options: Option (a) Kept my savings in the same asset class/classes, Option (b) Explored a new asset class, Option (c)Explored multiple new asset classes, Option (d) Added multiple new asset classes, and Option (e) Added multiple new asset classes but still exploring more options. Further, each of the options may be assigned a user score such as Option (a) may have a score of 1, Option (b) may have a score of 2, Option (c) may have a score of 3, Option (d) may have a score of 4 and Option (e) may have a score of 5. In this example, if the user selects Option (a) which is “Kept my savings in the same asset class/classes” then the user score is “1” which indicates that the user has a low curiosity level.

[050] In one example, the set of money sign may comprise eight (08) money signs and the money signs may be named as: money sign A, money sign B, money sign C, money sign D, money sign E, money sign F, money sign G, and money sign H. Further, each facet of the set of facets may be assigned a facet score on a scale of 1 to 5, and in terms of value, 1 may be understood as a lowest extreme and 5 may be understood as a highest extreme.

[051] In one example, a matching logic may be implemented wherein a match score may be computed as a full score, a moderate score, and a minor score by the scoring matrix and the deep learning algorithms. The full score, the moderate score, and the minor score may be provided to each user for each answer in the set of answers for each money sign using deep learning algorithms and the scoring matrix.

[052] Consider an example, wherein a user is scored for money sign A first. If the answer provided by the user corresponding to the ‘curiosity’ facet of the set of facets is given a user score as 1 by the scoring matrix, then the facet score 1 of money sign A for curiosity which is also 1 qualifies to be a ‘full match’. In other words, the match score of the user suggests that the facet of ‘curiosity’ of the user score is corresponding to the facet score of the Money sign A. Similarly, the scores for each of the set of answers may be scored using deep learning algorithms and the scoring matrix. Finally, the user score may be compared for all money signs A to H and the user may be assigned a money sign that has maximum user score.

[053] In one example, a test data for a test set of 100 users may be studied for identifying a set of facets corresponding to each of the 100 users. For instance, the set of facets may comprise but not be limited to a decision-making ability, a level of curiosity, a problem- solving ability, a risk-taking ability, an innovative quotient, a patience level, a temperament, a rationality and the like. It may be understood that the set of facets corresponding to the user, directly or indirectly affect the user’ s financial decisions and financial mindset.

[054] Further, the system 102 may assign a money sign with maximum user score to the user. In one example, the set of money signs may comprise 04 money signs and the money signs may be named money sign A, money sign B, money sign C, and money sign D. Further, each of the answer may be scored using the scoring matrix and the deep learning algorithms to assign a user score for each of the facet of the set of facets. For instance, the user score for money sign A may be calculated as 5, the user score for money sign B may be calculated as 4, the user score for money sign C may be calculated as 7, and the user score for money sign D may be calculated as 2. In this case, the user would be assigned money sign C as the user score is maximum for the money sign C.

[055] Furthermore, the system 102 may automatically extract a profile data of the user. The profile data may be understood to comprise a financial status, and a transaction history of the user. In one example the financial status of the user may be include but not be limited to an income status, a health insurance, a life insurance, and an asset portfolio. In other words, the financial status of the user may be determined based on several aspects of the financial condition of the user. Further, the transaction history may include but not be limited to an investment history of the user, a loan history, and an expenditure list of the user. In one example, the transaction history may provide all information about a user’s transactions in a term of 05 years. It may be understood that the financial status and the transaction history of the user may be linked to a unique identification number of the user. In one example, the unique identification number of the user may be an Income tax registered identity number. In another example, the unique identification number of the user may be a Permanent Account Number (PAN). In yet another example, the unique identification number may be a national identity number provided by a government of a country to the user to track all financial activities of the user.

[056] Therefore, the system 102 may use the unique identification number of the user to automatically extract a profile data for the user since each of the financial transactions of the user may be linked to the unique identification number.

[057] Further, the system 102 may create a user profile based on the money sign, the generation identifier (ID), and the profile data. The user profile may be understood as a data repository or collection of details about the user. The user profile may be used by the system 102 to access and display the data related to the user. It may be understood that the system 102 may automatically update the user profile based on changes in the profile data and the money sign.

[058] In one example, the system 102 may create a reference matrix for the user based on at least one profile data. The reference matrix may be understood as an illustrative arrangement of the user scores for each of the set of metrics, an ideal recommendation, a deviation score, more than one financial scores, and the net score. Each of the component of the reference matrix may be added as the component is determined and calculated. Therefore, the reference matrix may be completed at the final step of the resource allocation method. In one example, the user may access the reference matrix to understand the resource allocation at a glance. In one example, the user may choose to only refer to the resource allocation and not refer to the reference matrix.

[059] Further, the system 102 may determine an ideal recommendation for the user based on the generation ID and the user score through a machine learning model. It may be understood that the ideal recommendation is based upon a set of metrics.

[060] In one embodiment, the set of metrics may comprise 14 metrics in the set of metrics, as mentioned in Table 2 below:

Table 2

[061] Further it may be understood that there exists a relationship between the set of metrics and the set of facets. For instance, if ‘curiosity’ is considered as a facet and upon scoring using the deep algorithms, if the score for the facet curiosity is higher then, the set of metrics like ‘equity’, ‘passive income’, and ‘alternative investments’ may be recommended as an investment option to the user in the resource allocation. It may be understood that the curious user may get easily bored with mundane tasks and regular investments and hence explore the equity market share as equity allows the user to explore and experiment. Similarly, the user with a high curiosity level may find out of box solutions to earn money easily and passively. Therefore, passive income may be recommended for the user with higher level of curiosity.

[062] Subsequently, the system 102 may define a minimum threshold and a maximum threshold for the ideal recommendation based on the user score for each of the set of facets using deep learning algorithms. It may be understood that the ideal recommendation may be predefined for a user with a certain age and belonging to a particular generation ID. For instance, referring now to table 3:

Table 3 [063] It may be understood from above example in Table 3 that for a user belonging to a generation 3 with the generation ID as 3, i.e., the user has a generation 1 and a generation 2 earners in the family, the ideal recommendation comprises: 40% of investments of the user should be in a Expense and Liability Management, followed by 50% of investments in a Recommended Asset Allocation, and 10% of investments should be made towards an Emergency Planning. Similarly, for a user belonging to a generation 1 of a family, the emergency planning percentage would be 33% instead of 10% of the generation 3 user. It may be understood, that the age and the generational analysis of the user determines the ideal recommendation (%) for the user.

[064] Furthermore, Table 3 also mentions a minimum threshold and a maximum threshold for each of the metric in the set of metrics. Depending on the metric, the minimum threshold and the maximum threshold may be defined in a unit of a percentage, a value, and a multiple (x) format. For instance, the minimum threshold for liquidity-to-Expense ratio is 0.25x and the maximum threshold for liquidity-to-Expense ratio is 0.35x. However, the minimum threshold for the health insurance is Rupees 25 lacs and the maximum threshold for the health insurance is Rupees 100 lacs. In one embodiment, a machine learning model may be used to compute a minimum threshold and a maximum threshold for a user of a certain age and a particular generation using deep learning algorithms as explained in following paragraphs.

[065] Further, the system 102 may modify the ideal recommendation based on the user score for each of the set of facets, the reference matrix, the minimum threshold, and the maximum threshold. In other words, the system 102 may adjust or customize the ideal recommendation, based on the reference matrix, the minimum threshold and the maximum threshold. In one aspect, the deep learning algorithms may modify the ideal recommendation based on the money sign.

[066] In one aspect, the ideal recommendation may also be provided based on a set of macroeconomic indicators. The set of macroeconomic indicators may be related to a national economy a user is residing in and a national economy the user may be recommended to invest in. Further, as per the macroeconomic indicators and the national economy's status, the ideal recommendation may be modified to suggest appropriate investment options for the user.

[067] In one aspect the system 102 may involve deep learning algorithms to analyse and understand a dataset of users belonging to a similar financial status, with a same generation ID, and similar financial goals. The number of users in the dataset may be 1000. Further, the deep learning algorithms may compare the minimum threshold and the maximum threshold for each of the user and the ideal recommendation provided to the user. It may be understood that the dataset may identify optimal range of the minimum threshold and the maximum threshold for the users with similar financial status, generation ID and the profile data. Further, the deep learning algorithms may also track performance of the users in the dataset as a result of the ideal recommendations. This may help the deep learning algorithms to learn from the dataset and modify the ideal recommendation, the minimum threshold and the maximum threshold of the ideal recommendation accordingly.

[068] In one embodiment, the system 102 may ask a user to provide a financial aspiration of the user. Therefore, the ideal recommendation for the user may require to be adjusted as per the financial aspiration of the user.

[069] Furthermore, the system 102 may compute a deviation score of the user from the ideal recommendation upon modification. The deviation may be understood as a difference between an actual score of a user and a financial score of the user.

[070] Further, the financial score may be calculated by the system 102 based on a formula comprising the ideal recommendation (%) and the user actual value (%). Furthermore, the formula may be specific to each of the metric in the set of metrics.

[071] For example, for the metric “Good Liabilities-to-Total Assets”, the financial score may be calculated using the formula as below:

Financial Score =100-((100-50)/(Ideal recommendation % -0%)/100)*(Ideal recommendation-User actual %)*100

[072] For the present example, consider the ideal recommendation (%) as 20% and the user actual (%) as 19%. It may be understood that the ideal recommendation % and the user actual % are calculated from the ideal value (in lacs) as 213.0 and the user value (in lacs) as 200. Therefore, the financial score may be calculated as: 100-((100-50)/(20%-0%)/100)*(20%- 18.7793427230047%)* 100 = 97, hence the financial score may be calculated as 97.

[073] The financial score may be calculated for each of the metric in the set of metrics. The user actual value may be referred to as the user value in reality, and may be identified from the profile data of the user.

[074] Subsequently, the system 102 may calculate a net score for the user based on the financial score calculated for the user. It may be understood that the net score is calculated based on more than one financial score. [075] Further, the net score may be calculated by taking an average of the financial score for an expense and liability management, a recommended asset allocation, and an emergency planning calculated for the user as shown in Table 4 below:

Table 4

[076] It may be observed from Table 4 that a user’s actual percentage, and a user’s actual value of revenue may be used to modify the ideal recommendation in line with the user’s financial goals and aspirations as received by the system 102.

[077] Finally, the system 102 may recommend a resource allocation to the user based upon the net score, and the ideal recommendation. The resource allocation may be understood as a guidance, a plan, and a strategy for an asset allocation to the user to improve the net score and the financial condition of the user. In one example, the resource allocation may comprise an investment plan with a weightage for multiple types of investments. In one example, a user may be advised to invest 15 % in equity, 3% in cryptocurrency, 20% in Fixed deposits. In another example, a user may be advised to focus more on an emergency planning considering the age of the user belonging to a Generation 1 of the earners in the family. In another example, a user may be advised to invest more in low-risk investment options if the user is nearing an age of retirement.

[078] Referring again to the example in Table 4, further the system 102 may recommend resource allocation as per following Table 5:

Table 5

[079] It may be observed from above Table 5 that the net score of a user is calculated as 60. In one example, the net score may be calculated on a scale of 0 to 100 with 0 being minimum and 100 being maximum limit. Further, an inverse relationship may be established between the deviation score (%) and the net score. In other words, a low deviation may have a high net score because the deviation score of the user from the ideal recommendation is less. On the other hand, a high deviation score may result in a low net score. Depending on the deviation score, and the financial score, a resource allocation may be provided for each of the metric in the set of metrics.

[080] In one embodiment, the system 102 may also comprise receiving a feedback on the resource allocation from the user on the interface. In one example, the user may be prompted by the system 102 to provide a star rating on a scale of 1 to 5 stars. It may be understood that 1 star is a lowest limit and 5 star is a highest limit on the scale. In another example, the user may be prompted by the system 102 to answer a few questions about the resource allocation. In one example, the questions for feedback may be multiple choice questions, providing the user an opportunity to select one out of four options as an answer. In another example, the questions for feedback may allow the user to send a voice message narrating the feedback. Further, the system may apply Natural Language Processing (NLP) techniques to convert the voice message to a structured data format. In case of receiving a positive feedback from the user, the system 102 may provide an actionable insight to the user to implement the resource allocation. Further, the actionable insight may be understood as a strategy or a step wise protocol for the user to follow the resource allocation and increase the net score. In case of receiving a negative feedback from the user, the system 102 may repeat the above-mentioned steps again to recommend an alternative resource allocation to the user based upon the feedback from the user. It may be understood that the system 102 may keep providing the alternative resource allocation until the user provides the positive feedback. In one example, the system 102 may completely eliminate human intervention in recommending the actionable insights as well as the alternative resource allocation.

[081] Consider an example wherein a user named Dave is seeking an advice on comprehensive resource allocation using the system 102. Initially, Dave may access the system 102 using an interface and a user control. Further, Dave may create a login id and submit a national identity number. In next step, the system 102 may render a set of questions on the interface. Each question of the set of questions may be understood to be related to a set of facets. Further, Dave may go through the set of questions and submit a set of answers on the interface in response to the set of questions. In next step, the system may score the answers provided by Dave using a scoring matrix and deep learning algorithms. Further upon identifying the money sign maximum user score, the system 102 may assign a money sign from a set of money signs to Dave. Further, the system 102 may automatically extract a profile data of Dave using the national identity number of Dave. It may be understood that the national identity number may be unique to Dave. Further, the system 102 may create a user profile for Dave. Furthermore, the system 102 may determine an ideal recommendation for Dave for a set of metrics based on the generation ID using a machine learning model. The ideal recommendation may be understood to be based on the set of metrics. The set of metrics may primarily involve an expense and liability management, a recommended asset allocation, and an emergency planning. In next step, the system 102 may modify the ideal recommendation based on the money sign using deep learning algorithms within a minimum threshold and a maximum threshold. For instance, if the ideal recommendation for Dave is 70% then the system may consider Dave’s user scores. Further, a minimum threshold for the ideal recommendation may be 10% and a maximum threshold for the ideal recommendation may be 50%. Therefore, the system may modify Dave’s ideal recommendation to be 60% considering the set of metrics and Dave’s user scores. Further, the system 102 may determine a financial score for the user for each of the set of metrics based on the profile data of the user. In next step, the system 102 may compute a deviation score of Dave from the ideal recommendation after modification. For example, the deviation score may be a difference between the ideal values and an actual value of every set of metrics for the user. Further, the deviation score may be calculated in percentage. After knowing the deviation, the system may accordingly compute a deviation score of the user by comparing the financial score with the ideal recommendation upon modification for each of the set of metrics. Subsequently, a net score for Dave may be calculated by the system 102 based on more than one financial score and the deviation score. Lastly, a resources allocation may be recommended to Dave based upon the net score, and the ideal recommendation. If Dave agrees with the resource allocation, a feedback may be provided to the system 102 and Dave will be provided insights to implement the resource allocation. If Dave requires any changes or modifications in the resource allocation, the system 102 may provide an alternative resource allocation to Dave. The goal of the invention is to help Dave improve the net score from present value to a better value. For instance, if the net score of Dave is calculated by system 102 as 60, then the resource allocation recommended would increase the net score of Dave from 60 to 90 in a span of three years. Maximum net score achievable by Dave is 100.

[082] Referring now to figure 2, a method 200 for recommending a resource allocation to a user is shown, in accordance with an embodiment of the present subject matter. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types. [083] The order in which the method 200 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 200 or alternate methods for recommending a resource allocation to a user in real time. Additionally, individual blocks may be deleted from the method 200 without departing from the scope of the subject matter described herein. Furthermore, the method 200 for recommending the resource allocation to the user in real time on a platform can be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method 200 may be considered to be implemented in the above-described system 102.

[084] At block 202, a request for resource allocation may be received from a user. It may be understood that the request may be received through a selection of a user control and on an interface of a system.

[085] At block 204, a set of questions may be rendered on the interface for the user to answer. The set of questions may be related to a set of facets.

[086] At block 206, a set of answers may be received from the user in response to the set of questions. The set of answers may be received on the interface of the system.

[087] At block 208, the set of answers may be scored to generate a user score for each of the set of answers. Each of the set of answers corresponds to each of the set of facets.

[088] At block 210, a money sign from a set of money signs may be assigned to the user based on the user score, and the set of answers.

[089] At block 212, a profile data of the user may be automatically extracted. The profile data may comprise a financial status, and a transaction history.

[090] At block 214, a user profile based on the money sign, a generation identifier (ID) and the profile data may be created. The user profile may be unique to the user.

[091] At block 216, an ideal recommendation may be determined for the user for a set of metrics based on the generation ID using a machine learning model.

[092] At block 218, the ideal recommendation may be modified based on the money sign using deep learning algorithms for the set of metrics. The modification is within a minimum threshold, and a maximum threshold for the ideal recommendation.

[093] At block 220, a financial score may be determined for the user for each of the set of metrics based on the profile data of the user.

[094] At block 222, a deviation score of the user may be computed from the ideal recommendation upon modification. [095] At block 224, a net score may be calculated for the user based on more than one financial score.

[096] At block 226, a resource allocation may be recommended to the user based upon the net score, and the ideal recommendation.

[097] Figure 3 illustrates an example view of a vector space 300. In particular embodiments, an object or an n-gram may be represented in a d-dimensional vector space, where d denotes any suitable number of dimensions. Although the vector space 300 is illustrated as a three- dimensional space, this is for illustrative purposes only, as the vector space 300 may be of any suitable dimension.

[098] In particular embodiments, an n-gram may be represented in the vector space 300 as a vector referred to as a term embedding. Each vector may comprise coordinates corresponding to a particular point in the vector space 300 (i.e., the terminal point of the vector). As an example and not by way of limitation, vectors 310, 320, and 330 may be represented as points in the vector space 300, as illustrated in Figure 3.

[099] As an example and not by way of limitation, a dictionary trained to map text to a vector representation may be utilized, or such a dictionary may be itself generated via training. As another example and not by way of limitation, a model, such as Word2vec, may be used to map an n-gram to a vector representation in the vector space 300. In particular embodiments, an n- gram may be mapped to a vector representation in the vector space 300 by using a machine leaning model (e.g., a neural network). The machine learning model may have been trained using a sequence of training data (e.g., a corpus of objects each comprising n-grams).

[100] In particular embodiments, an object may be represented in the vector space 300 as a vector referred to as a feature vector or an object embedding. In particular embodiments, an object may be mapped to a vector based on one or more properties, attributes, or features of the object, relationships of the object with other objects, or any other suitable information associated with the object.

[101] As an example and not by way of limitation, an object comprising a video or an image may be mapped to a vector by using an algorithm to assign a money sign to a user. Features used to calculate the vector may be based on information obtained from edge detection, corner detection, blob detection, ridge detection, scale-invariant feature transformation, edge direction, changing intensity, autocorrelation, motion detection, optical flow, thresholding, blob extraction, template matching, Hough transformation (e.g., lines, circles, ellipses, arbitrary shapes), or any other suitable information. [102] As another example and not by way of limitation, an object comprising audio data may be mapped to a vector based on features such as a spectral slope, a tonality coefficient, an audio spectrum centroid, an audio spectrum envelope, a Mel-frequency cepstrum, or any other suitable information. Although this disclosure describes representing an n-gram or an object in a vector space in a particular manner, this disclosure contemplates representing an n-gram or an object in a vector space in any suitable manner.

[103] In particular embodiments, the system 102 may calculate a similarity metric of vectors in vector space 400. The similarity metric may be a cosine similarity, a Minkowski distance, a Mahalanobis distance, a Jaccard similarity coefficient, or any suitable similarity metric. The similarity metric of two vectors may represent how similar the two objects or n-grams corresponding to the two vectors, respectively, are to one another, as measured by the distance between the two vectors in the vector space 300. As an example and not by way of limitation, vector 310 and vector 320 may correspond to objects that are more similar to one another than the objects corresponding to vector 310 and vector 330, based on the distance between the respective vectors. Although this disclosure describes calculating a similarity metric between vectors in a particular manner, this disclosure contemplates calculating a similarity metric between vectors in any suitable manner.

[104] Referring now to Figure 4 illustrating an example artificial neural network (“ANN”) 400 of the deep learning algorithms. In particular embodiments, an ANN may refer to a computational model comprising one or more nodes. Example ANN 400 may comprise an input layer 410, hidden layers 420, 430, 460, and an output layer 450. Each layer of the ANN 400 may comprise one or more nodes, such as a node 405 or a node 415. In particular embodiments, each node of an ANN may be connected to another node of the ANN. As an example and not by way of limitation, each node of the input layer 410 may be connected to one of more nodes of the hidden layer 420.

[105] In particular embodiments, one or more nodes may be a bias node (e.g., a node in a layer that is not connected to and does not receive input from any node in a previous layer). In particular embodiments, each node in each layer may be connected to one or more nodes of a previous or subsequent layer. Although Figure 4 depicts a particular ANN with a particular number of layers, a particular number of nodes, and particular connections between nodes, this disclosure contemplates any suitable ANN with any suitable number of layers, any suitable number of nodes, and any suitable connections between nodes. As an example and not by way of limitation, although Figure 4 depicts a connection between each node of the input layer 410 and each node of the hidden layer 420, one or more nodes of the input layer 410 may not be connected to one or more nodes of the hidden layer 420.

[106] In particular embodiments, an ANN may be a feedforward ANN (e.g., an ANN with no cycles or loops where communication between nodes flows in one direction beginning with the input layer and proceeding to successive layers). As an example and not by way of limitation, the input to each node of the hidden layer 420 may comprise the output of one or more nodes of the input layer 410. As another example and not by way of limitation, the input to each node of the output layer 450 may comprise the output of one or more nodes of the hidden layer 460. In particular embodiments, the ANN may be a deep neural network (e.g., a neural network comprising at least two hidden layers). In particular embodiments, the ANN may be a deep residual network. A deep residual network may be a feedforward ANN comprising hidden layers organized into residual blocks. The input into each residual block after the first residual block may be a function of the output of the previous residual block and the input of the previous residual block. As an example and not by way of limitation, the input into residual block N may be F(x)+x, where F(x) may be the output of residual block N~l, x may be the input into residual block N-l. Although this disclosure describes a particular ANN, this disclosure contemplates any suitable ANN.

[107] In particular embodiments, an activation function may correspond to each node of an ANN. An activation function of a node may define the output of a node for a given input. In particular embodiments, an input to a node may comprise a set of inputs. As an example and not by way of limitation, an activation function may be an identity function, a binary step function, a logistic function, or any other suitable function.

[108] In particular embodiments, the input of an activation function corresponding to a node may be weighted. Each node may generate output using a corresponding activation function based on weighted inputs. In particular embodiments, each connection between nodes may be associated with a weight. As an example and not by way of limitation, a connection 425 between the node 405 and the node 415 may have a weighting coefficient of 0.4, which may indicate that 0.4 multiplied by the output of the node 405 is used as an input to the node 415. In particular embodiments, the input to nodes of the input layer may be based on a vector representing an object. Although this disclosure describes particular inputs to and outputs of nodes, this disclosure contemplates any suitable inputs to and outputs of nodes. Moreover, although this disclosure may describe particular connections and weights between nodes, this disclosure contemplates any suitable connections and weights between nodes. [109] In particular embodiments, the ANN may be trained using training data. As an example and not by way of limitation, training data may comprise inputs to the ANN 400 and an expected output. As another example and not by way of limitation, training data may comprise vectors each representing a training object and an expected label for each training object. In particular embodiments, training the ANN may comprise modifying the weights associated with the connections between nodes of the ANN by optimizing an objective function.

[110] As an example, and not by way of limitation, a training method may be used (e.g., the conjugate gradient method, the gradient descent method, the stochastic gradient descent) to backpropagate the sum-of-squares error measured as a distances between each vector representing a training object (e.g., using a cost function that minimizes the sum-of-squares error). In particular embodiments, the ANN may be trained using a dropout technique. As an example, and not by way of limitation, one or more nodes may be temporarily omitted (e.g., receive no input and generate no output) while training. For each training object, one or more nodes of the ANN may have some probability of being omitted. The nodes that are omitted for a particular training object may be different than the nodes omitted for other training objects (e.g., the nodes may be temporarily omitted on an object-by-object basis). Although this disclosure describes training the ANN in a particular manner, this disclosure contemplates training the ANN in any suitable manner.

[111] Exemplary embodiments discussed above may provide certain advantages. Though not required to practice aspects of the disclosure, these advantages may include those provided by the following features.

[112] Some embodiments of the system and the method promote effective and focused resource allocation for individual investors.

[113] Some embodiments of the system and the method provide unbiased and practical resource allocation to the user.

[114] Some embodiments of the system and the method help the user to evaluate their financial condition in real time.

[115] Some embodiments of the system and the method enable the user to find appropriate resource allocation as per customizable investment preference, generational analysis, and age.

[116] Although implementations for methods and system for recommending a resource allocation to a user in real time on an interface have been described in language specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of implementations for recommending a resource allocation to a user in real time on an interface.