Kowshik-18 / credit_score_engine

Our industrial attachment project involves developing a credit scoring system to determine Upay users' loan eligibility. This system uses machine learning to forecast loan approval using transaction history and customer data. This project aims to provide a reliable credit score system for loan disbursement. It will also inform decision makers about

upay_loan_prediction

The project focuses on developing a credit scoring system for Upay users using machine learning techniques, leveraging various data sources to predict loan eligibility with precision. This system aims to streamline loan disbursement decisions and provide valuable insights to decision-makers. Additionally, an automated user interface is being developed to facilitate faster decision-making.

Features

• Use of machine learning to predict the likelihood of a user receiving a loan
• Delivery of an efficient and precise credit scoring system
• Facilitation of loan disbursement decision-making
• Offer of insights into customer loan eligibility and the potential loan amount they could receive

User Interface

We have created a demo user interface using react in the front-end and django in the back-end along with the integration of our trained machine learning model.

Home Page

This is the project's homepage, where it outlines the project. In the navbar there is another button that will redirect the user to the loan eligibility test page.

Loan Eligibility Test Page

Users can submit customer information and transaction histories as a csv file to this page. The user will receive a success notification after uploading them. After inputting the information, the user will be sent to the loan prediction result page.

Success Notification for Uploading

Loan Prediction Result Page

This page shows the results of loan eligibility using customer information and transaction history of customers. This information is fed into the machine learning model, and it shows the wallet number, name, status, available packages, and amount of the loan based on their status, percentages of eligibility, non-eligibility and under consideration.

Documentation:

https://docs.google.com/document/d/1Vv-o3vLFDROEZuxc5snFZp-YmE00O3Ii/edit?usp=sharing&ouid=114144251286523500250&rtpof=true&sd=true

Supervised By:

👤 Nahid Hossain

• LinkedIn: @nahossain
• GitHub: @mnhmilu

Contributors

👤 Arif Mohammad Asfe

• LinkedIn: @arifasfe
• GitHub: @arifasfe

👤 Mohammad Akbar Bin Shah

• LinkedIn: @mohammad-akbar2603
• GitHub: @smhproduct

👤 Ahammed Zayed Uddin Rahat

• LinkedIn: @ahammed-zayed-uddin-rahat-18cse
• GitHub: @Zayed-Rahat

👤 Rajarshi Sen

• GitHub: Rajarshi-sen24
• LinkedIn: @rajarshi-sen-5ab5b61bb

👤 Antu Chowdhury

• LinkedIn: @antu-chowdhury-167045200

👤 Kowshik Chowdhury

• LinkedIn: @kowshik-chowdhury-44419819a
• GitHub: @Kowshik-18