Description:FIELD OF INVENTION:
[1] The present disclosure generally relates to the field of invention in information technology, specifically focusing on the method and system of the credit score evaluation. This approach is poised to redefine credit evaluation, providing financial institutions with a more reliable and efficient method for gauging borrowers creditworthiness, especially when the traditional credit scores are unavailable.
BACKGROUND AND PRIOR ART:
[2] The background information herein below relates to the present disclosure but is not necessarily prior art. A credit score serves as a numerical representation of the financial reliability of an individual, business, or entity. Over the life of an individual there may be different events that can be relevant (directly or indirectly) to the creditworthiness of a person.
[3] Credit scoring commonly occurs before granting access to credit or approving loan applications. Creditors or lenders utilize credit scores to assess the potential risk associated with extending credit to a borrower. These scores guide lenders in determining a borrower's eligibility for a loan and appropriate credit limits. Credit scores generated by conventional techniques may not be available for every individual. [4] Presently only a small number of credit bureaus generate credit scores using data from limited data sources. It can be difficult to confirm the veracity and integrity of the data sources. The consumer may not understand how their credit score is generated. The consumer might not be notified when data is submitted that impacts their credit score.
Conventional methods of scoring rely heavily on past credit data to determine borrowers' risk profiles. Yet, for underprivileged individuals lacking extensive credit histories, accessing such scores poses challenges, limiting their financial opportunities.
[5] The proposed system bridging the credit assessment gap for underprivileged individuals. By leveraging alternative data and advanced analytics, this innovative scoring method promotes financial inclusion, empowering marginalized communities to access the resources needed for prosperity.
OBJECTS OF THE INVENTION:
[6] Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows:
[7] It is an object of the present disclosure to ameliorate one or more problems of the prior art or to at least provide a useful alternative.
[8] An object of the present disclosure is to provide a system for computing the creditworthiness of an individual in the absence of conventional credit scores. The foremost aim is to provide an alternative credit scoring system tailored to individuals, particularly those from underprivileged strata, who lack access to traditional credit scores.
[9] Another object of the present disclosure is to facilitate emergency loan accessibility and streamline the process of seeking loans, especially during emergency situations.
[10] Another object of the present disclosure is to promote financial inclusion. By offering an accessible credit scoring solution, the invention aims to empower underprivileged individuals with the means to participate in the formal financial system, access essential financial services, and unlock opportunities for economic advancement.
[11] Yet another object of present disclosure is to provide seamless integration with the various stakeholders like financial institutions and the underprivileged individuals.
[12] Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY OF THE INVENTION:
[13] The present disclosure envisages a system and method of computing creditworthiness of an underprivileged individual.
[14] The system include a hardware device in the form of a smart mobile phone, a backend server to compute the creditworthiness score and a laptop/computer device for the financial institutions to review loan applications and lend money.
[15] The mobile application is configured to receive the end user information. The end user registers himself with his mobile number which is used as an authentication medium in subsequent logins.
[16] The user can compute his creditworthiness score if he hasn’t already calculated in the recent past. The user is prompted a questionnaire containing questions to capture the basic details like monthly income, educational qualifications, number of dependents in his/her family, asset details etc.
[17] The SMS Module is configured to receive a dump of the SMS data residing in the recipient’s mobile device. The mobiles data is taken with the consent of the user. When SMS data is received, the backend servers filter the SMS data, retaining only financial-related messages while discarding non-relevant ones. The filtered messages undergo further analysis.
[18] The utility module is configured to receive the user’s data on the utility bill payments like electricity, water, phone etc. which is collected either directly or from a third-party service.
[19] The compute creditworthiness module is configured to evaluate the credit score. The credit score is computed based on the speech to text, utility module and SMS extraction module data. The recommended list of banks that are willing to lend money for the generated credit score is shared to the user.
[20] The creditworthiness score is computed in the backend systems. This score is a conglomeration of three individual scores namely – Adjusted Q-score, SMS score, Utility score. Each of the aforementioned scores is calculated in different manner thereby making the approach unique and accommodative.
[21] While the adjusted Q-score involves calculating a preliminary Q-score using mathematical formulae followed by application of a machine learning technique, the SMS score is calculated by analyzing the financial transaction data captured by the mobile phone. The utility score is calculated, by analyzing the payment history for various utility services.
[22] The security aspects involve authentication of the user as well as the bank. Appropriate permissions are taken from the user to ensure privacy is safeguarded.
[23] The present system Niramaya Credit Score is a novel system and method for evaluating the Credit score, specifically designed for individuals, particularly those from underprivileged backgrounds, which do not have access to conventional credit scores. Utilizing various data sources and applying machine learning techniques such as regression techniques and classification models, in conjunction with statistical methods, this scoring system delivers a thorough evaluation of creditworthiness.
BRIEF DESCRIPTION OF DRAWINGS:

[24] A Niramaya Credit score system and method of computing creditworthiness of an underprivileged individual, the present disclosure will now be described with the help of the accompanying drawing, in which:
Figure 1, depicts a block diagram of credit score system, in accordance with an embodiment of the present disclosure.
Figure 2, illustrates overall workflow of the system, in accordance with an embodiment of the present disclosure.
Figure 3, illustrates the overall method used to compute creditworthiness score, in accordance with an embodiment of the present disclosure.
Figure 4, illustrates the evaluation of adjusted Q-score in accordance with an embodiment of the present disclosure.
Figure 5, illustrates the evaluation of SMS score in accordance with an embodiment of the present disclosure.
Figure 6, illustrates users, channels and security embodiments of the present disclosure.
The proposed system shows the efficient method for gauging borrowers creditworthiness, especially when the traditional credit scores are unavailable.
DETAILED DESCRIPTION:
[25] Embodiments, of the present disclosure, will now be described with reference to the accompanying drawing.
[26] Embodiments are provided so as to thoroughly and fully convey the scope of the present disclosure to the person skilled in the art. Numerous details are set forth, relating to specific components, and methods, to provide a complete understanding of embodiments of the present disclosure. It will be apparent to the person skilled in the art that the details provided in the embodiments should not be construed to limit the scope of the present disclosure. In some embodiments, well-known processes, well-known apparatus structures, and well-known techniques are not described in detail.
[27] The terminology used, in the present disclosure, is only for the purpose of explaining a particular embodiment and such terminology shall not be considered to limit the scope of the present disclosure. As used in the present disclosure, the forms "a,” "an," and "the" may be intended to include the plural forms as well, unless the context clearly suggests otherwise. The terms "comprises," "comprising," “including,” and “having,” are open-ended transitional phrases and therefore specify the presence of stated features, elements, modules, units and/or components, but do not forbid the presence or addition of one or more other features, elements, components, and/or groups thereof. The particular order of steps disclosed in the method and process of the present disclosure is not to be construed as necessarily requiring their performance as described or illustrated. It is also to be understood that additional or alternative steps may be employed.
[28] The foregoing description of the specific embodiments so fully reveals the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
[29] Throughout this specification the word “comprise”, or variations such as “comprises” or “comprising”, will be understood to imply the inclusion of a stated element, step, or group of elements, steps, but not the exclusion of any other element, step, or group of elements, or steps.
[30] While considerable emphasis has been placed herein on the components and component parts of the preferred embodiments, it will be appreciated that many embodiments can be made and that many changes can be made in the preferred embodiments without departing from the principles of the disclosure. These and other changes in the preferred embodiment as well as other embodiments of the disclosure will be apparent to those skilled in the art from the disclosure herein, whereby it is to be distinctly understood that the foregoing descriptive matter is to be interpreted merely as illustrative of the disclosure and not as a limitation.

[31] The present disclosure envisages a system and method of computing creditworthiness of an underprivileged - A Niramaya Credit score.
[32] The system comprises several components, including a hardware device as a smart mobile phone, which serves as a user interface for individuals interacting with the credit scoring system. Additionally, there is a backend server infrastructure responsible for computing the creditworthiness score based on the collected data and implemented algorithms. This server handles data processing, analysis, and score generation, ensuring accuracy and efficiency in the evaluation process. Furthermore, financial institutions are provided with a separate device, such as a laptop or computer, equipped with the basic software tools like web browser to review loan applications and make lending decisions based on the computed credit scores. This multi-component system facilitates seamless communication and collaboration between users, ensuring a smooth and reliable process for accessing credit services.
[33] The algorithm for determining an individual’s credit score relies on three key parameters: credit score calculation through utility bill payments, through financial SMS messages, and through questionnaire data provided during the application process.
[34] These parameters serve as fundamental pillars in the evaluation of the individual’s creditworthiness, encompassing diverse aspects of their financial behavior and history. By scrutinizing utility bill payments, the algorithm assesses the individual’s consistency and timeliness in meeting financial obligations, thereby gauging their reliability in managing credit.
[35] Similarly, analysis of financial SMS messages provides insights into the individual’s spending patterns, financial habits, and potential risk factors, contributing to a comprehensive assessment of their creditworthiness.
[36] Additionally, questionnaire data gathered during the application process offers valuable information regarding the individual’s financial circumstances, goals, and risk tolerance, further refining thecredit evaluation process. Through the integration of these parameters, the algorithm establishes a robust frameworkfor accurately quantifying the individual’s credit risk and facilitating informed decision-making by lenders and financial institutions.

The method of calculating the credit score of the proposed system:
Module 1: Computing credit score using financial SMS messages
[37] The Financial SMS Analyzer algorithm is a Python-basedcode/algo designed to analyze financial transactions extracted from SMS messages. It extracts relevant information suchas transaction amounts, dates, vendor names, and transaction
types from SMS messages related to financial activities. The algorithm provides insights into spending habits and categorization of transactions based on machine learning models.
• Input:The input for deriving the credit score encompasses financial transaction data, primarily sourced from SMS notifications.These messages contain details of various aspects, including payments, purchases, debits, credits and other non-transactional related messages. These input messages are then filtered and only transactional related SMS messages are taken into account.
• Data Extraction: Extract key information such as transaction amounts, dates, vendor names, and transaction types from SMS messages using Regular expression.
• Standard formatted list: The extracted date and balance is then formatted according to the use case.
• Analysis: Analyze extracted data to provide insights into spending patterns and categorization of transactions.
• Categorization: Categorize transactions into necessary and unnecessary based on predefined categories such as health, utilities, groceries, bar etc.
• Credit Score Calculation: Calculate credit scores based on transaction patterns and available balances.
Module 2: Computing credit score using utility bill payments Input
[38] The utility bill payment algorithm prompts the user to input two values: the number of regularly paid months and the total days delayed. These inputs are then used to compute payment history score. Additionally, the number of months delayed is automatically calculated within the script by subtracting the number of regularly paid months from 12, representing a full year. These values are passed as arguments, which then computes the payment history score based on the provided inputs. If the user inputs are not valid integers, an error message is displayed, indicating that valid integers should be entered.
Module 3: Computing credit score using questionnaire
[39] Inputs: For calculating the questionnaire score we take inputs from the user while signing-up for our app.The inputs taken are income,state, highest education level, housing status, house rent(if any),number of dependencies in the family ,if spouse is employed(if married),type of government scheme participation and benefit amounts. We are taking per capita income, average household size of each state from official Government sites.
There are multiple functions ,we are using to calculate the final score
• Lifestyle score
• Score calculated from Applicant income, highest education
• level and rental status are included here
• Family responsibility score
• Score calculated from Applicant Dependents numbers and if
• Spouse employed(if married) are included
• Government benefits
Figure 1 depicts the system diagram outlining the comprehensive functionality of the proposed system.
[40] The system depicted in this figure comprises three main components: the user 101, a mobile application, and backend systems. Users 101, interact with the mobile application to exchange data, with the mobile app serving as the intermediary between users 101 and the backend systems.
[41] Data utilized for computing the creditworthiness score is sourced from three primary channels: questionnaire responses 102, utility payments data 103, and SMS data 104. The questionnaire responses 102, is configured to receive an input via a speech-to-text, module integrated within the mobile application. SMS data 104, is configured to store in the user's 101 mobile device, is extracted with appropriate permissions granted by the user. Similarly, utility payments data 103, module is configured to collect and utilize for score calculation purposes.

[42] Once the necessary data is collected and processed within the mobile application, it is transmitted to the backend servers for further analysis and computation of the credit, 105. These backend systems employ advanced algorithms and data processing techniques to generate accurate credit scores based on the provided data.
[43] In summary, the user interacts with the mobile application to provide relevant data, which is then transmitted to the backend systems for credit score computation. This integration of user input, mobile application functionality, and backend processing ensures a seamless and efficient credit evaluation process.
Figure 2, illustrates overall workflow of the system, in accordance with an embodiment of the present disclosure.
[44] The provided diagram illustrates the operational flow of the application, commencing from user registration and authentication, culminating in the submission of loan applications to recommended banks. To start 201 the process, users are required to download and install the application on their smartphones, followed by entering 202 their mobile number upon app launch. Subsequently, users undergo authentication procedures 203, enabling access to the application’s Home screen 204 upon successful verification.
[45] For first-time users, additional basic user details are collected during the authentication process 203 to facilitate account setup. Upon accessing the application, users have the capability to compute their creditworthiness score 205 directly within the app. However, to capture essential SMS data necessary for creditworthiness evaluation, users must grant requisite permissions upon request.
[46] To initiate the creditworthiness evaluation process 205, users are prompted to complete a questionnaire embedded within the application. This questionnaire gathers pertinent information utilized in generating the creditworthiness score. Following completion, the generated score is promptly displayed on the user's screen for review.
[47] Upon computation of the creditworthiness score 205, the application provides users with a curated list of banks 207, willing to extend credit based on the generated score 206. Users can then proceed to submit loan applications 208, to one or more banks from the recommended list, tailored to their specific credit requirements.

[48] In summary, the application streamlines the process of credit evaluation and loan application, offering users a convenient and user-friendly platform to assess their creditworthiness and access credit from recommended financial institutions.
Figure 3, illustrates the overall method used to compute creditworthiness score, in accordance with an embodiment of the present disclosure.
[49] The provided diagram offers a comprehensive overview of the components involved and the methodology employed in computing the creditworthiness score. The final score is determined through the amalgamation of three distinct scores: the SMS score 301, utility score 302, and adjusted Q-score 303. Each of these scores is derived utilizing various techniques outlined in subsequent diagrams.
[50] Specific weights, denoted as w1, w2, and w3, are allocated to the SMS score 301, utility score 302, and adjusted Q-score 303, respectively. These weights are assigned based on the relative importance of each individual score in assessing creditworthiness. To calculate the final score,each weight is multiplied by its corresponding score, and the resultant values are summed. Subsequently, an average is computed to derive the final creditworthiness score 304, which is subsequently displayed to the user via the application interface, as depicted in Figure 2.
[51] In essence, this methodology employs a weighted averaging technique to integrate multiple scores, providing users with a comprehensive assessment of their creditworthiness within the application interface.
Figure 4, illustrates the evaluation of adjusted Q-score in accordance with an embodiment of the present disclosure.
[52] This diagram elucidates the methodology employed in calculating one of the components of the creditworthiness score, known as the adjusted Q-score 406. The process initiates with the collection of a comprehensive dataset, termed the golden dataset 401, obtained through an extensive survey. This dataset encompasses various details such as individual income, assets, marital status, ration card details, educational qualifications, among others. The survey targets 220 individuals, primarily from underprivileged segments, who are anticipated to utilize our application.
[53] A fundamental prerequisite for deploying any machine learning model is the availability of sufficient data for training. To augment the dataset, standard data augmentation techniques are employed to generate a larger dataset 402, while preserving the original properties of the golden dataset 401. This augmentation process is validated by verifying the statistical measures of dispersion for both datasets.
[54] Subsequently, a preliminary Q-score 403 is computed for each data point within the augmented dataset 402, utilizing specific parameters including:
1. Income
2. Residing state
3. Highest education level
4. Housing status (owned or rented)
5. House rent (if applicable)
6. Number of dependents in the family
7. Spouse employment status (if married)
8. Participation in government schemes and associated benefit amounts
[55] Basic mathematical formulae, statistical measures, and aggregation techniques are applied to derive the preliminary Q-score for each data point.
[56] This preliminary Q-score 403, is then incorporated into the augmented dataset 402. Subsequently, the dataset, inclusive of the preliminary Q-score 403, is utilized to train a regression model 404, which is then serialized as a pickle (.pkl) file. For each new user seeking their creditworthiness score, their data is fed into this trained regression model 404. The output of this model yields the adjusted Q-score 405, aimed at assimilating the underlying patterns within the dataset to compute the Q-score for the current user. This adjusted Q-score 405 forms an integral component of the final creditworthiness score.
Figure 5, illustrates the evaluation of SMS score in accordance with an embodiment of the present disclosure.
[57] This diagram depicts the process of computing the SMS score, as mentioned in Figure 3. When a user seeks to compute their creditworthiness score, the application requests permission to access and read the user's SMS data stored on their mobile phone. Upon obtaining user consent, the SMS data is extracted from the device in the form of a dump 501 and transmitted to the backend servers for analysis.
[58] Once received, the backend servers filter the SMS data 502, retaining only financial-related messages while discarding non-relevant ones. The filtered messages undergo further analysis, wherein specific details are extracted 503 from each message as mentioned below:
1. The date of transaction,
2. Transaction type,
3. Amount,
4. Vendor,
5. Balance.
These details are then structured and stored in repository 503, as a list of tuples in Python, facilitating streamlined data analysis.
[59] Three insights are derived from this processed data:
1. Expenditure Analysis 504: The expenditure patterns of the user are analyzed by categorizing transactions into various predefined categories such as Food, Medicine, Entertainment, Liquor, Travel, etc. Each category is further classified as Necessary, Unnecessary, or Unsure. A scoring mechanism is applied to assess the prudence of the user's spending habits, employing a Naïve Bayes classifier for classification.
2. Balance Trend Analysis 505: Concurrently, the trend in available balances over the past few months is analyzed. Statistical measures of dispersion such as mean and standard deviation are utilized to assess the stability and consistency of the user's balance trend. A score is assigned based on this analysis.
3. Credit Transaction Percentage 506: The wealth management index is estimated by computing the ratio of net credit transactions to total transactions. This ratio is converted into percentage. It provides insights into the user's financial behavior, indicating the proportion of credit-type transactions relative to the total number of transactions. It also indicates how often the user involves in credit type transactions.
[60] As depicted in the figure, weights (w1, w2, and w3) are assigned to each of the derived indices: Expenditure Analysis score, Balance Trend Analysis score, and Credit Transaction Percentage. These weights are multiplied with their respective indices and averaged to yield the SMS score 506, which forms an integral component of the overall creditworthiness assessment.
Figure 6, illustrates users, channels and security embodiments of the present disclosure.
[61] This diagram illustrates the interactions between various stakeholders within the system, accompanied by the implemented security framework. The system caters to two primary sets of end-users:
1. Individuals 601, seeking financial assistance, typically belonging to the underprivileged category.
2. Financial institutions 602, predominantly lenders such as banks and micro-finance institutions.
End-users engage with the system through the utilization of a mobile phone 603, serving as the primary channel of interaction. Two key security protocols are enforced for end-users belonging to the first category (loan seekers):
1. Authentication 604: User identification is facilitated through OTP-based authentication, ensuring secure access to the system.
2. SMS Permission 605: End-users are prompted to grant read access permissions for SMS data, allowing for comprehensive creditworthiness assessment.
[62] On the other hand, lenders 602 interact with the system via a web portal accessible through desktop or laptop devices 604. This portal serves as a platform for lenders 602, to access a curated list of potential borrowers, alongside their corresponding creditworthiness scores. Lenders 602, are empowered to make informed lending decisions based on their preferences, including the approval 607 or denial of loan applications. The web portal operates seamlessly through the utilization of REST APIs, ensuring efficient data exchange and interaction between the portal and the underlying system.
[63] As part of the security framework, financial institutions, represented by banks 602, are mandated to undergo authentication 604 using unique passwords. This additional layer of authentication 604, ensures secure access for authorized personnel within financial institutions, empowering them to make lending decisions while safeguarding sensitive data and transactions.
[64] In summary, the system fosters secure and efficient interactions between individuals seeking financial assistance and financial institutions through the implementation of robust security protocols and a user-friendly web portal interface.

TECHNICAL ADVANCES AND ECONOMICAL SIGNIFICANCE
[65] The present disclosure described hereinabove has several technical advantages including, but not limited to, is driven by the following three primary objectives:
• Alternative Credit Score Accessibility: The foremost aim is to provide an alternative credit scoring system tailored to individuals, particularly those from underprivileged strata, who lack access to traditional credit scores such as CIBIL. By offering an alternative scoring method, the invention seeks to address the financial inclusion gap for marginalized communities and ensure equal access to financial opportunities.
• Facilitating Emergency Loan Accessibility: Another key objective is to streamline the process of seeking loans, especially during emergency situations. By providing a readily available credit score, individuals can expedite loan applications, thus enabling faster access to crucial financial assistance when needed most.
• Promotion of Financial Inclusion: Central to the invention objectives is the promotion of financial inclusion. By offering an accessible credit scoring solution, the invention aims to empower underprivileged individuals with the means to participate in the formal financial access essential financial services, and unlock opportunities for economic advancements.
[66] Through the attainment of these objectives, the Niramaya Credit Score invention endeavors to enhance financial accessibility, resilience, and inclusion for individuals across diverse socioeconomic backgrounds. , C , C , Claims:We claim:
1. A method for determining a credit score of an applicant during an application process, comprising: receiving a plurality of financial messages from at least one user equipment of said applicant; receiving at least one transactional data corresponding to at least one utility bill payment performed by said applicant; Calculating a credit score based on said received plurality of financial messages; Calculating a credit score based on said received at least one transactional data utility bill payment corresponding to said at least one utility bill payment; and Calculating a credit score based on questionnaire data provided by said applicant during the application process; wherein the credit score is determined by evaluating a plurality of parameters including a financial behavior and history.
2. The method of claim 1, wherein a Financial SMS Analyzer is employed to analyze financial transactions extracted from SMS messages, by employing following steps:
a. Extracting pertinent information, including transaction amounts, dates, vendor names, and transaction types, from said plurality of financial messages associated with financial activities of said applicant; and
b. Generating at least one spending pattern based on said extracted pertinent information.
3.The method of claim 1, includes a step of categorizing transactions by employing at least one machine learning model.
4.The method of claim 1, includes a step of automatically determining the number of months delayed by subtracting the number of regularly paid months from 12, representing a full year.
5.The method of claim 1, includes a step of displaying an error message if the applicant’s inputs are not valid integers, indicating that valid integers should be entered.
6. The method of claim 1, includes a step of
a. Obtaining a plurality of inputs from said applicant during the application signup process, wherein said plurality of inputs includes income, state of residence, highest level of education attained, housing status, house rent (if applicable), number of dependents in the family, marital status, and employment status of spouse (if married), type of government scheme participation, and associated benefit amounts;
7. The method of claim 1, includes a step of retrieving per capita income and average household size data from official Government sources for each state; and
8. The method of claim 1, includes a step of utilizing the applicant-provided inputs and obtained data to calculate a questionnaire score as part of evaluating creditworthiness.