YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
AutoSafe Recall Prediction Model
LightGBM binary classifier predicting automotive recall risk from NHTSA complaint data.
- Task: Binary classification (will vehicle be recalled?)
- Training data: 140,488 NHTSA complaints (2015-2025)
- F1 Score: 60.5% | Recall: 70.2% | ROC-AUC: 0.916
- Threshold: 0.338
- Features: 1,025 (TF-IDF + component + temporal + severity)
Once uploaded your files will be at:
https://huggingface.co/YOUR-USERNAME/recall-model/resolve/main/production_model.pkl
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support