Comparing the Effectiveness of Machine Learning Models in Credit Risk Assessment

Abstract

      In the banking sector, credit risk management is becoming increasingly complex and crucial in the context of globalization. Credit risk is one of the primary challenges for financial institutions when borrowers fail to fulfill debt repayment obligations as promised. To mitigate this risk, machine learning methods have become important tools in assessing individual borrowing capabilities. In this study, we compare the performance of four popular machine learning models: Decision Tree, Random Forest, Support Vector Machine, and Logistic Regression in credit risk assessment. The data underwent testing and analysis, showing that the Random Forest model outperformed the others, with the highest accuracy of 93.22 %. These results provide profound insights into the applicability of machine learning models in credit risk assessment and may assist financial institutions in making decisions regarding individual credit issuance.