joshleh/secom-fault-detection

End-to-end fault detection pipeline on SECOM semiconductor manufacturing data. Compares Isolation Forest, Random Forest, and LSTM Autoencoder with MLflow experiment tracking. Includes SHAP explainability and a FastAPI inference endpoint that returns top contributing sensor features per prediction.

22
/ 100
Experimental
No Package No Dependents
Maintenance 13 / 25
Adoption 0 / 25
Maturity 9 / 25
Community 0 / 25

How are scores calculated?

Stars

Forks

Language

Jupyter Notebook

License

MIT

Last pushed

Mar 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/joshleh/secom-fault-detection"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.