metadata
license: mit
tags:
- predictive-maintenance
- engine-health
- tabular-classification
- logistic-regression
Engine Health Predictive Maintenance Model
This model predicts whether an engine requires maintenance based on sensor readings.
Model
Best model: Logistic Regression
Target
- 0: Normal engine condition
- 1: Faulty / maintenance required
Business Metric
Recall was prioritized because missing unhealthy engines can cause breakdowns, downtime, and repair cost.
Evaluation Results
- Accuracy: 0.6415
- Precision: 0.5111
- Recall: 0.6886
- F1-Score: 0.5867
- ROC-AUC: 0.7002