A machine learning project to detect fraudulent credit card transactions using classification models.
This project demonstrates data preprocessing, feature engineering, model building, and evaluation using Python and popular ML libraries.
Credit card fraud is a significant problem in financial services.
This project applies supervised machine learning techniques to detect fraudulent transactions from imbalanced datasets.
- Data preprocessing and handling missing values
- Handling class imbalance with SMOTE / undersampling
- Feature scaling
- Model training with multiple ML algorithms (Logistic Regression, Random Forest, XGBoost, etc.)
- Evaluation using accuracy, precision, recall, F1-score, and ROC-AUC
- Visualization of results (confusion matrix, ROC curve, etc.)
Credit-Card-Fraud-Detection/ │── data/ # Sample data or dataset link │── notebooks/ # Jupyter notebooks │── src/ # Source code │── requirements.txt # Dependencies │── README.md # Project documentation