ST Model Accuracy
Out-of-sample backtests of the skater projection engine — projections vs. what actually happened, graded on a full-season (per-82-GP) basis against a simple baseline
Skater projections
Beat the baseline by 8% on out-of-sample accuracy · p10–p90 coverage 81% (2025-26 backtest, 4,968 preds)
Player Accuracy
per 82 GP vs Baseline · 4,968 predsskill 8%p10–p90 cov 81%
| Stat | N | Model | Base | Skill | Cov |
|---|---|---|---|---|---|
| Scoring | |||||
| Points | 623 | 8.52 | 8.91 | +4% | 80% |
| Goals | 623 | 4.53 | 4.72 | +4% | 75% |
| Assists | 623 | 5.94 | 6.39 | +7% | 80% |
| Power Play | |||||
| PP Points | 623 | 3.25 | 3.64 | +11% | 82% |
| Shooting | |||||
| Shots | 623 | 20.89 | 22.77 | +8% | 83% |
| Peripheral | |||||
| Hits | 615 | 24.68 | 29.12 | +15% | 81% |
| Blocks | 615 | 12.94 | 15.48 | +16% | 81% |
| PIM | 623 | 12.11 | 12.18 | +1% | 82% |
Game Model — Out-of-Sample Backtest
backtest
| Season | Games | Brier | Base | Win% | Margin MAE | Total MAE | Vegas MAE | Beat% |
|---|---|---|---|---|---|---|---|---|
| 2025-26 | 1,312 | 0.2474 | 0.2495 | 53% | 2.13 | 1.9 | — | — |
| 2024-25 | 1,312 | 0.2355 | 0.2461 | 60% | 2.13 | 1.9 | — | — |
| 2023-24 | 1,230 | 0.2348 | 0.2486 | 61% | 2.13 | 1.9 | — | — |
| 2022-23 | 1,230 | 0.2360 | 0.2498 | 60% | 2.11 | 1.8 | — | — |
| 2021-22 | 1,230 | 0.2293 | 0.2483 | 64% | 2.08 | 1.9 | — | — |
| 2020-21 | 812 | 0.2339 | 0.2487 | 60% | 2.04 | 1.9 | — | — |
| 2019-20 | 1,012 | 0.2430 | 0.2489 | 55% | 2.05 | 1.8 | — | — |
| Overall | 8,138 | 0.2372 | 0.2485 | 59% | 2.10 | 1.9 | — | — |
The model's pre-game win probability is scored by Brier against every completed game's outcome; a Brier below the home-field Basemeans it adds signal beyond "home teams win." Margin/Total MAE measure the projected score. Vegas MAE / Beat% read — for this sport: the free odds feed carries no historical closing lines yet, so those columns populate as line history accrues.