• K Gnana Reddy
• Dr. BOLLOLU RAJESH KUMAR

Credit card fraud is a major challenge in the financial sector, necessitating advanced detection techniques to prevent unauthorized transactions and minimize losses. This study presents a hybrid machine learning model that integrates XGBoost for supervised learning and Isolation Forest for unsupervised anomaly detection, enhancing fraud detection accuracy. The model is trained on real-world transaction data, leveraging SMOTE for handling class imbalances and feature engineering for improved performance. To enable real-time fraud detection, the system incorporates Apache Kafka for transaction streaming and a Flask API for instant fraud prediction. The hybrid approach effectively reduces false positives while maintaining high precision and recall. Experimental results demonstrate superior ROC-AUC scores compared to traditional methods, highlighting the system’s potential as a secure, scalable, and efficient fraud detection framework for financial institutions.

: Credit Card Fraud Detection, Machine Learning, XGBoost, Isolation Forest, Anomaly Detection, Real-Time Streaming, Apache Kafka, Flask API, SMOTE, Hybrid Model, Financial Security.

"Enhancing Real-Time Credit Card Fraud Detection Using a Hybrid Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 3, page no.c440-c444, March-2025, Available :http://www.jetir.org/papers/JETIR2503254.pdf

"Enhancing Real-Time Credit Card Fraud Detection Using a Hybrid Machine Learning Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 3, page no. ppc440-c444, March-2025, Available at : http://www.jetir.org/papers/JETIR2503254.pdf