KHL Prediction Accuracy Sign in
All project features are currently free Why the project runs on donations →
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 →
57.7%168 evaluated games

Model and baseline

Validated games
318
Majority-class baseline
50.6%
Lift, percentage points
7.1
Brier score
0.2429

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

Winner: 50% threshold; selected totals and periods: 52%
MarketCorrect / evaluatedAccuracy
Winner incl. OT/SO97 / 16857.7%
Over 4.5 / Under 5.5100 / 17656.8%
Period 1 · Over/Under 1.523 / 4057.5%
Period 2 · Over/Under 1.520 / 4050.0%
Period 3 · Over/Under 1.523 / 6634.8%

Accuracy by confidence

ConfidenceGamesPredicted probabilityActual accuracy
70%+1071.7%50.0%
60–69%6263.9%69.4%
55–59%5257.7%46.2%
50–54%4452.6%56.8%

Winner accuracy by team

TeamCorrect / evaluatedAccuracy
Металлург Мг15 / 2171.4%
Салават Юлаев8 / 2040.0%
ЦСКА14 / 1877.8%
Торпедо13 / 1872.2%
Авангард9 / 1850.0%
Динамо Мн7 / 1838.9%
Ак Барс8 / 1747.1%
Локомотив12 / 1675.0%
Динамо М11 / 1668.8%
Адмирал10 / 1566.7%
Барыс4 / 1526.7%
ХК Сочи10 / 1471.4%
Амур7 / 1450.0%
Драконы7 / 1450.0%
Спартак7 / 1450.0%
Лада12 / 1392.3%

Prediction accuracy is measured in games involving each team; the model can also choose its opponent. Small samples are unstable.