This study used a bank loan database to check the applicability of the borrower classification model and examined machine learning techniques. I developed auxiliary vector machine models, decision trees, and random forests, and compared their prediction accuracy with benchmarks based on logistic regression models. They analyzed the performance indicators based on the overall ranking. My results show that the performance of Random Forest is better than other models. In addition, the performance of the support vector machine model is poor when using linear and non-linear kernels. My results show that banks have the opportunity to create value. Improve standard predictive models by researching machine learning techniques.

Keywords : Machine Learning, Artificial Intelligence, Supervised learning, Classification, Regression, Tensorflow.