Model transparency
Pre-game model performance
Evaluate the NHL pre-game win probability model using overall accuracy, confidence ranges, probability calibration, rolling trends, and team-level results.
Filters apply to the overall summary, confidence analysis, calibration, rolling accuracy, and team-level view.
Overall results
Model summary
Completed games for Model V2 matching the selected season and game type.
XGBoost · Model V2 · Updated nightly · Completed games through yesterday
Prediction quality
Accuracy by confidence range
This shows how often Model V2’s predicted winner was correct within each predicted home-team win-probability range.
| Predicted home-win range | Games | Correct predictions | Accuracy |
|---|---|---|---|
| No bucketed performance data available for this filter selection yet. | |||
No confidence-range data available
Bins use 10% increments. Low sample means fewer than 30 completed games.
Probability quality
Probability calibration
Calibration compares average predicted home-team win probability with the actual home-team win rate in each range.
| Predicted home-win range | Games | Average predicted | Actual home-win rate | Difference |
|---|---|---|---|---|
| No calibration data available for this filter selection yet. | ||||
No calibration data available
Difference equals actual home-win percentage minus average predicted percentage.
Positive values mean home teams won more often than predicted.
Trend
Overall model accuracy over time
Rolling Model V2 accuracy across completed games using a 25-game window.
No overall accuracy trend data available for this filter selection
Team analysis
Team-level model view
Select a team to compare average Model V2 probability, actual win rate, favorite and underdog records, and a rolling 10-game trend.
ANA
Rolling 10-game model probability versus actual win rate.
Updating team view…
One line shows rolling average model probability. The other shows actual
rolling win rate over the same 10-game span.
What the model predicts
The model estimates the home team’s chance of winning before puck drop.
When predictions are created
Predictions are generated before each game and are not updated live.
How results update
Accuracy, confidence buckets, and calibration update as completed games enter the nightly pipeline.
Early-season caution
Predictions may shift more early in the season because less current-season data is available.
Playoff filters
Playoff sections remain empty until completed playoff games are available.
Data source
Results and statistics are based on official NHL data, with models updated nightly.