Model History
Keep the model accountable.
Model history gives the scanner a trust layer: what changed, why confidence moved, and how the model performed by market over time.
Open NBA ScannerTransparent changes
Model changes should be visible and reviewable instead of buried behind a single score.
Preset history
Signal changes
Confidence movement
Market-level reporting
Performance context
The point is not to claim certainty. The point is to understand where the model has evidence.
Confidence bands
Market splits
Sample-size awareness
Replay and audit context