Intelligent Decision Support System for Loan Evaluation Using Machine Learning

Abstract

Banks heavily rely on loans as a primary revenue source, yet accurately identifying deserving applicants who will reliably repay loans remains challenging. Conventional methods often struggle to sift through numerous applicants effectively. To address this issue, an innovative machine learning (ML)-based loan prediction system has been introduced to identify qualified loan applicants autonomously. This study includes comprehensive data prepossessing, effective data balancing using SMOTE, and implementing diverse ML models: logistic regression, decision trees, random forests, support vector machines, K-nearest neighbors, and naive Bayes. Performance metrics such as accuracy, recall, and F1-score rigorously evaluate the models. The experimental analysis highlights Random Forest as the top performer, achieving 81.9% accuracy. A user-friendly web application has been developed for user interaction.