Hybrid Lightweight Anomaly Detection for Credit Card Fraud

Credit card fraud has become a major challenge in modern digital payment systems,requiring fast, accurate, and scalable fraud detection solutions. This paper proposes a Hy-brid Lightweight Anomaly Detection System designed to identify fraudulent transactionsin real time with minimal computational overhead. The framework integrates statistical Z-Score filtering, Isolation Forest–based unsupervised anomaly scoring, and Logistic Regres-sion for interpretable fraud probability estimation. The system processes transaction datathrough optimized preprocessing, feature engineering, and hybrid scoring to capture bothrare outliers and subtle fraudulent patterns. Experimental evaluation using a benchmarkcredit card fraud dataset demonstrates that the proposed method achieves high accuracy(96.1strong recall for fraud cases, and extremely low inference time (¡0.02 seconds pertransaction), making it suitable for real-time fintech applications. The lightweight designensures easy deployment on low-resource environments while maintaining high reliabilityand transparency. The proposed system enhances financial security by reducing false pos-itives, improving early fraud detection, and offering a scalable solution for modern digitalpayment ecosystemsKeywords:Credit Card Fraud Detection, Hybrid Anomaly Detection, Li