Machine Learning Based Credit Card Fraud Detection System
This project uses Machine Learning algorithms to identify fraudulent credit card transactions. Multiple models were trained and compared using various performance metrics.
The final model selected was XGBoost due to its superior fraud detection performance, excellent ROC-AUC score, and minimal overfitting.
Credit Card Transaction Dataset with fraud and legitimate records.
9 machine learning algorithms were trained and evaluated.
XGBoost achieved the best performance among all tested models.