Open model evaluation
KHL prediction accuracy
One latest pre-match version per game. This page evaluates model probabilities; the selected published picks and skips have their own results ledger.
Selected picks and skips →69.0%42 evaluated games
Model and baseline
Validated games
42
Majority-class baseline
64.3%
Lift, percentage points
4.7
Brier score
0.2219
The baseline always selects the most common outcome in this same sample. Lower Brier scores indicate better probabilities, including confidence in incorrect predictions.
Accuracy by market
| Market | Correct / evaluated | Accuracy |
|---|---|---|
| Winner incl. OT/SO | 29 / 42 | 69.0% |
| Over/Under 5.5 in regulation | 2 / 3 | 66.7% |
| Period 1 · Over/Under 1.5 | 28 / 42 | 66.7% |
| Period 2 · Over/Under 1.5 | 20 / 42 | 47.6% |
| Period 3 · Over/Under 1.5 | 19 / 42 | 45.2% |
Accuracy by confidence
| Confidence | Games | Predicted probability | Actual accuracy |
|---|---|---|---|
| 70%+ | 0 | — | — |
| 60–69% | 15 | 64.0% | 80.0% |
| 55–59% | 14 | 58.4% | 50.0% |
| 50–54% | 13 | 52.7% | 76.9% |
Winner accuracy by team
| Team | Correct / evaluated | Accuracy |
|---|---|---|
| Локомотив | 6 / 7 | 85.7% |
| Металлург Мг | 6 / 7 | 85.7% |
| Авангард | 4 / 7 | 57.1% |
| Ак Барс | 3 / 7 | 42.9% |
| Салават Юлаев | 5 / 6 | 83.3% |
| Торпедо | 5 / 6 | 83.3% |
| ЦСКА | 4 / 6 | 66.7% |
| Динамо Мн | 0 / 5 | 0.0% |
| Амур | 3 / 3 | 100.0% |
| Лада | 3 / 3 | 100.0% |
| СКА | 3 / 3 | 100.0% |
| Нефтехимик | 2 / 3 | 66.7% |
| Драконы | 1 / 3 | 33.3% |
| Адмирал | 2 / 2 | 100.0% |
| Динамо М | 2 / 2 | 100.0% |
| Северсталь | 2 / 2 | 100.0% |
Prediction accuracy is measured in games involving each team; the model can also choose its opponent. Small samples are unstable.