Predictive Maintenance – Best Model
Overview
This model predicts whether an engine requires maintenance using sensor readings.
Training Data
Loaded from Hugging Face dataset: SabarnaDeb/Capstone_PredictiveMaintenance (train.csv / test.csv).
Best Model
- Algorithm: AdaBoost
- Best CV F1: 0.7745
- Best Parameters: {'learning_rate': 0.05, 'n_estimators': 100}
Test Performance
- Accuracy: 0.6304
- Precision: 0.6304
- Recall: 1.0000
- F1: 0.7733