Predicting Long-Term Deposit Openings of Bank Customers Using Decision Tree and Random Forest Classification

Resumen

In recent years, banks have faced challenges in providing credit facilities due to customers' credit risk, prompting the implementation of customer validation systems to mitigate risk. Credit risk directly affects bank profitability, making it a significant concern for banks. Classification and clustering can both be valuable tools for analyzing customer behavior. This study focuses specifically on the classification process for bank customers' data, with the goal of identifying those who open long-term deposits and those who do not. Independent variables describing customer performance within the banking system are used in the classification process, with the decision tree and random forest methods being employed.