An Efficient Machine Learning-Based Approach for Credit Card Fraud Detection and Prevention

Credit card fraud poses a major financial risk in digital transactions. This study presents a machine learningbased fraud detection system using Logistic Regression, Decision Tree, Random Forest, and XGBoost to classify transactions as fraudulent or legitimate. The model preprocesses data, applies feature scaling, and evaluates performance using accuracy, F1-score, and ROC-AUC metrics. A fraud retrieval feature allows users to analyze suspicious transactions. This approach enhances fraud detection efficiency, reduces false positives, and improves financial security.