• Pankaj Gupta
• Gaurav Gupta
• Vaishnavi Kasurde
• Pranjali Gurnule

This Credit card fraud poses a significant threat to financial systems worldwide, necessitating advanced detection mechanisms. This paper presents a comprehensive machine learning-based system for real-time credit card fraud detection. The proposed approach integrates traditional machine learning models, such as Random Forest, with deep learning techniques like Autoencoders for anomaly detection. Additionally, Explainable AI (XAI) methods, specifically SHAP (SHapley Additive exPlanations), are employed to enhance model interpretability. The system is evaluated on the Kaggle Credit Card Fraud Detection Dataset, achieving an F1-score of 0.85 and an AUC-ROC score of 0.98. Experimental results demonstrate the system's effectiveness in detecting fraudulent transactions while providing actionable insights for stakeholders. The integration of real-time detection, anomaly identification, and interpretability makes this approach a robust solution for modern fraud detection challenges.

Credit Card Fraud Detection, Machine Learning, Random Forest, Autoencoder, SHAP, Explainability, Anomaly Detection.

"AN ADVANCED MACHINE LEARNING APPROACH FOR CREDIT CARD FRAUD DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.f102-f110, March-2025, Available :http://www.jetir.org/papers/JETIR2503537.pdf

"AN ADVANCED MACHINE LEARNING APPROACH FOR CREDIT CARD FRAUD DETECTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppf102-f110, March-2025, Available at : http://www.jetir.org/papers/JETIR2503537.pdf