NHL Model Accuracy
Out-of-sample backtests of the goalie projection engine — projections vs. what actually happened, graded per stat against the Marcel baseline — rate skills (SV%/GAA) directly, counting stats over a full starter workload
Goalie projections
Beat the Marcel baseline by 7% on out-of-sample accuracy · p10–p90 coverage 54% (2025-26 backtest, 248 preds)
Player Accuracy
per-game rate vs naive · 248 predsskill 7%p10–p90 cov 54%
| Stat | N | Model/g | Base/g | Skill | Cov |
|---|---|---|---|---|---|
| Rate | |||||
| Save % | 62 | 0.0122 | 0.0132 | +8% | 52% |
| GAA | 62 | 0.3031 | 0.3265 | +7% | 58% |
| Volume | |||||
| Saves | 62 | 111.3248 | 123.144 | +10% | 48% |
| Shutouts | 62 | 1.914 | 1.9582 | +2% | 56% |
Team Game Model vs Home-Ice Baseline
backtest
| Season | Games | Brier | Base | Acc | Margin MAE | Total MAE |
|---|---|---|---|---|---|---|
| 2025-26 | 1,252 | 0.2526 | 0.2494 | 53.1% | 2.17 | 1.84 |
| 2024-25 | 1,242 | 0.2469 | 0.2460 | 57.3% | 2.18 | 1.88 |
| 2023-24 | 1,170 | 0.2447 | 0.2488 | 57.4% | 2.19 | 1.84 |
| 2022-23 | 1,164 | 0.2398 | 0.2500 | 59.9% | 2.13 | 1.83 |
| 2021-22 | 1,169 | 0.2385 | 0.2483 | 61.6% | 2.14 | 1.86 |
| 2020-21 | 749 | 0.2425 | 0.2491 | 58.2% | 2.11 | 1.86 |
| 2019-20 | 942 | 0.2505 | 0.2490 | 55.0% | 2.09 | 1.84 |
| Overall | 7,688 | 0.2452 | 0.2486 | 57.5% | 2.15 | 1.85 |
Opponent-adjusted goal-differential ratings (SRS) → predicted margin, win probability, and total, scored walk-forward (ratings built only from games played before each matchup — no leakage). A lower Brier than the home-ice baseline means real predictive skill; NHL is a high-variance, near-coin-flip league, so honest edges are small. The model never sees the betting line.