Enhancing Financial Decision-Making: Predictive Modeling for Personal Loan Eligibility with Gradient Boosting, XGBoost, and AdaBoost

This study aims to improve the prediction of personal loan eligibility through the application of advanced machine learning techniques. Accurate prediction of creditworthiness is crucial for financial institutions to mitigate risks and optimize their lending processes. We evaluated three algorithms Gradient Boosting, XGBoost, and AdaBoost using a comprehensive dataset containing demographic and banking information. Among these, XGBoost proved to be the most effective model, achieving an accuracy of 0.95, precision of 0.95, recall of 0.95, and an F1 score of 0.95. These results demonstrate XGBoost's superior ability to accurately identify individuals likely to repay loans, making it an invaluable tool for enhancing decision-making in loan approvals. By leveraging XGBoost, banks can reduce the risk of defaults, streamline their operations, and provide better customer service, ultimately leading to more efficient and reliable lending strategies.