by bpleone
LIVE

Model Residuals

Calibration gives you one bias number per market. Residuals (actual − predicted) tell you where the model is systematically wrong. Mean residual < 0 means the model is over-predicting; > 0 means under-predicting. The histogram shows how the misses are distributed; the worst-misses table shows which exact plays broke the model.

Refreshed every morning by python/residuals.py after outcomes settle. Trailing 30-day window. See also Self-Learning for the bias correction that actually fires on tomorrow's projections.

Loading residuals...

Per-Player Systematic Patterns
PlayerMarketnMean residualMAESuggested action

Loading player patterns...

Park-Specific Bias

Loading park residuals...

Where does the model break per stadium? Parks with strong residuals suggest the model's park_factor multiplier is mis-calibrated for that venue.

Handedness-Specific Bias

Loading handedness residuals...

LHB vs RHB residuals. Skew in one direction suggests the model isn't accounting for platoon splits sharply enough.