Abstract:

In this study, a model for validating real bank customers using machine learning algorithms is presented. Important customer characteristics were selected from 15 indicators identified from the literature and industry experts. Then, data obtained from a commercial bank were validated through various machine learning algorithms such as random forest, decision tree, Navi Bayes, support vector machine, logistic regression, gradient boosting, and nearest neighbor. The algorithms were evaluated through four evaluation criteria including accuracy, precision, coverage, and F-test. After evaluating the models, the best machine learning algorithm was selected. The results showed that random forest performed better than other algorithms and achieved the highest accuracy with an accuracy of 93.33 percent.