Tuned XGBoost (RandomizedSearchCV) for the same task; best CV F1 among those checkpoints.
Weights were tuned on your Kaggle Spotify–style track dataset and derived labels; redistribution of raw Spotify data may be constrained by Kaggle/dataset terms—the model weights are yours to license under MIT, but you should not imply Spotify endorses the model.
license: mit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support