<![CDATA[The rapid growth of digital payment systems has increased the complexity and risk of credit card fraud, particularly due to the highly imbalanced nature of transaction data. This study aims to compare the performance of Random Forest and XGBoost algorithms combined with the Synthetic Minority Over sampling Technique in detecting fraudulent credit card transactions. The proposed approach focuses on improving classification effectiveness by addressing class imbalance and reducing bias toward legitimate transactions. Data preprocessing includes normalization, stratified data splitting, and the application of over sampling techniques on the training dataset. Model performance is evaluated using precision, recall, F score, and the area under the receiver operating characteristic curve, which are more appropriate for imbalanced classification problems. The findings indicate that Random Forest demonstrates more stable and balanced performance, particularly in minimizing false fraud alerts while maintaining adequate fraud detection capability. These results suggest that Random Forest with over sampling provides a practical and reliable solution for real world credit card fraud detection systems.]]>
Copyrights © 2026
