• Navyashree
• Keerthana K S
• Lekhankrishna Kulkarni
• Shwetha M

Detection of Credit Card fraud in any financial transaction has been a big challenge as volumes of transactions handled using advanced machine learning techniques have been a fantasizing dream. The present work reports analysis of a complete dataset comprising 284,807 credit card transactions using a Random Forest and an XGBoost classifier for identifying frauds. In this work, the SMOTE technique has been used to handle the inherent class imbalance problem, and further, the performance evaluation for each model has been done by considering the metrics: Our random forest model yields an AUC-ROC score of 0.99 with a precision rate of 0.95 in fraud detection. Conclusively, other ethics discussions on the implications and social impacts of automated fraud detection systems have also been discussed in the presented research. Results obtained from this study will no doubt spur serious boosts toward the development of robust fraud detection mechanisms, especially in balancing training data in machine learning applications with regard to financial security. It carries out an analysis of credit card fraud using three different machine learning algorithms: Random Forest, XGBoost, and K-Nearest Neighbors. From the comparison analysis, it can be seen that the best performance by Random Forest is 0.99, XGBoost's is 0.98, and the performance of KNearest Neighbors is 0.97 concerning AUC-ROC with SMOTE balanced classes.

Credit Card Fraud Detection,Machine Learning,Random Forest ,XGBoost,K-Nearest Neighbors (KNN),SMOTE,Ensemble Learning,Imbalanced Dataset,AUC-ROC,Financial Fraud,Real-Time Detection,Feature Engineering,Fraud Analytics,Synthetic Oversampling,Model Evaluation Metrics

"THE DETECTION OF CREDIT CARD FRAUD ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.h413-h418, July-2025, Available :http://www.jetir.org/papers/JETIR2507755.pdf

"THE DETECTION OF CREDIT CARD FRAUD ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pph413-h418, July-2025, Available at : http://www.jetir.org/papers/JETIR2507755.pdf