Credit Fraud Detection System

Project Structure

• src/preprocessing.py: Data loading, scaling, and SMOTE for handling class imbalance.
• src/model.py: Random Forest model definition and evaluation.
• train.py: Main script to execute the training pipeline.
• app.py: Flask backend to serve predictions.
• templates/index.html: Premium web interface for testing the model.
• creditcard.csv: Dataset (Kaggle).

How to Run

1. Install Dependencies:
   pip install -r requirements.txt
2. Train the Model:
   python train.py
3. Run the Application:
   python app.py
4. Access the UI: Open http://127.0.0.1:5000 in your browser.

Model Details

• Algorithm: Random Forest Classifier
• Preprocessing:
  • Standard scaling for Time and Amount.
  • SMOTE (Synthetic Minority Over-sampling Technique) to balance the dataset.
• Evaluation Metrics: Precision, Recall, and F1-Score are used due to heavy class imbalance.