Book III · Chapter 1
Metrics, calibration, and decisions
Start with confusion counts, test probability quality, then choose an operating threshold or abstention rule.
Chapter contents
6 entries · read in order- 01 Confusion matrix and classification metrics✓ Concept
- 02 Precision, recall, and F1✓ Concept
- 03 ROC, PR curves, and AUC✓ Concept
- 04 Calibration: when your model says 80% it should be right 80% of the time✓ Concept
- 05 Expected Calibration Error (ECE)✓ Concept
- 06 Decision thresholds, asymmetric costs, and abstention✓ Concept