The goal of this research is to develop a model for forecasting loan defaults. This type of strategy is unavoidable since bad loans are a critical problem in the financial sector. To address this issue, a literature analysis has been conducted to study the significant factors that lead up to and solve this problem. Dense Neural Network with Dropout (ANN with Deep Learning), XGBoost, Random Forest, Logistics Regression, and Support Vector Classifier are the approaches utilized. We have compared the models' accuracies, performance, and confusion matrix measures during the experimental phase. The best approach has been chosen, described, and suggested based on these factors. Our final results are based on the number of defaulters predicted and actualized, while we have also suggested a model if we prefer institutional research that prioritized accuracy, performance, and speed.

Keywords : Credit Score, Logistic Regression, XGBoost.