International Journal of Scientific Research and Engineering Development

Credit risk is one of the major challenges faced by banks and financial institutions when approving loans for customers. Financial organizations must carefully analyze whether a borrower has the ability to repay the loan without defaulting. Incorrect credit decisions may lead to financial losses and increase the risk for lending institutions. Therefore, an efficient and reliable credit risk evaluation system is necessary to support decision-making. This project, “Credit Risk Prediction System Using Machine Learning and Web-Based Interface” aims to develop an automated system that predicts the credit risk level of loan applicants sing financial and personal data. The system uses a Random Forest Classifier to analyze features such as age, income, employment status, loan amount, credit history, and debt ratio. These parameters help the model identify patterns and determine whether an applicant is likely to repay the loan or default. A Flask-based web application is developed to allow administrators to upload datasets, train the machine learning model, and perform real-time predictions based on user inputs. The system processes the entered data and classifies applicants into categories such as Low Risk, Medium Risk, and High Risk. This helps financial institutions make faster and more accurate loan approval decisions. The project demonstrates how machine learning techniques can improve credit risk assessment by providing a data-driven and automated approach for financial decision-making.

Ajay R, Dr.K.Banuroopa,"Credit Risk Prediction and Loan Suggestion System Using Financial Data" International Journal of Scientific Research and Engineering Development, V9(2): Page(579-599) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.