SignalForge is a deployable fraud-detection API built from a Random Forest classifier trained on the PaySim financial transaction dataset.
- Fraud classification using Random Forest
- Probability-based fraud scoring
- FastAPI REST API with Swagger UI
- Simple JSON request payload
PaySim Financial Transaction Dataset
- Algorithm: Random Forest Classifier
- Accuracy: 97.49%
- ROC-AUC: 99.79%
pip install -r requirements.txt
uvicorn app:app --reload --port 8001Open:
http://127.0.0.1:8001/docs
curl -X POST "http://127.0.0.1:8001/predict" \
-H "Content-Type: application/json" \
-d @sample_request.json