assessing and validating bank customers using data mining algorithms for home loan

All over the world, the banking industry is one of the most important pillars of any country's economy and due to the provision of various financial and credit services, it plays a decisive role in the development and economic growth of the country and it can be described as the driving force that accelerates, balances, and organizes the economy. given that banks' capital is less than the total value of their assets, even if a percentage of the loans are not receivable, banks face bankruptcy risk. in order to reduce the volume of claims, validation of loan applicants can be very effective. data mining techniques and algorithms are one of the methods of validating bank customers. in this study, considering the current and past data of bank customers to receive loan facilities analyzed by data mining algorithms such as decision trees, k nearest neighbor algorithm (knn), support vector machine (svm) and random forest to identify good and bad customers. finally, the ability of these algorithms to validate banking customers will be examined. according to the results, random forest algorithm has a better ability to classify customers.