Risk Analysis for Home Credit Default

Housing Loan prediction is a major challenge for many financial Organizations since predicting correct outcome can reduce the risk and improve the decision-making during the process of loan. This study includes a machine learning-based method that predicts home loans default based on real-time data such as borrowers, financial profiles, credit history, and loan amount. The preprocessing tasks like handling missing data and normalization of numerical features are performed to guarantee data quality. The process of model building increased prediction accuracy by combining several algorithms such as logistic regression, decision trees, and integration methods. Important performance metrics like accuracy, precision, recall, and F1 score are calculated to test the model performance. This analysis gives lenders a clearer picture of the most important factors that determine default rate.