<![CDATA[Non-performing loans are a significant problem for financial institutions as they can disrupt economic stability and cause financial losses. To address this issue, this study applies the Support Vector Machine (SVM) algorithm combined with the Synthetic Minority Over-sampling Technique (SMOTE) to improve the accuracy of classifying customers at risk of loan default. The study compares three kernel functions: linear, polynomial, and RBF. The experimental results show that the RBF kernel achieves the best performance with an accuracy of 0.76 (76%), followed by the polynomial kernel at 0.73 (73%) and the linear kernel at 0.72 (72%). This approach proves effective in improving credit risk prediction accuracy through data distribution balancing using SMOTE.]]>
Copyrights © 2026
