Credit card fraud is a significant challenge in digital financial transactions, causing financial losses to customers, banks, and financial institutions. Traditional fraud detection systems rely on predefined rules and manual verification, which may fail to identify complex and continuously changing fraudulent patterns. This project proposes an artificial-intelligence-based credit card fraud detection system using machine learning to classify financial transactions as legitimate or potentially fraudulent. The system uses the publicly available European credit card fraud detection dataset from Kaggle. Data preprocessing, feature scaling, and class-imbalance handling with class weighting are applied. SMOTE is not used. Logistic Regression is the baseline classifier, and Random Forest is the primary classifier. The system integrates a Python backend with a MySQL database and a web interface. The application is an academic demonstration and does not connect to a live banking or payment network.

Kanisya E, Harini S, Indhumathi S, Keerthika L, Dr. K. Pradeepa,"Credit Card Fraud Detection Using Machine Learning" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(5): Page(820-825) September - October 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.