🏒 NHLForecasts.com
Data-Driven NHL Predictions & Analytics
2026-27 Preseason

Our Methodology

Transparency is a core principle of NHLForecasts. This page explains exactly how our prediction model works — from the data it ingests to the probabilities it outputs — so you can evaluate the forecasts on their merits rather than taking them on faith.

Model Overview

Every game prediction is produced by blending two complementary machine-learning models:

The final win probability starts with a 50/50 average of both models. Production win probabilities use the raw model blend, without post-processing calibration.

Model Inputs & Features

The model uses 13 features derived from recent team and goalie performance. All features use walk-forward construction — only data available before each game is used — to prevent data leakage.

Feature CategoryExamplesPurpose
Rolling Win Rate Home-minus-away win percentage (30 games) Recent team form
Goal Differential Goals scored minus allowed per game (30-game window) Margin of victory / defeat
Goalie Performance Recent save percentage of projected starter Starting goaltender quality
Roster Quality Lagged on-ice xG ratings Recent roster contribution
Rest & Schedule Days since last game (both teams) Fatigue and back-to-back effects

Win Probability Production

For each upcoming game the pipeline:

  1. Builds features from the latest available data
  2. Runs both models to get raw probabilities
  3. Averages the two outputs (50% logistic + 50% GBC)
  4. Production win probabilities use the raw model blend, without post-processing calibration.
  5. Outputs a home-win probability (away = 1 − home)

We evaluate the model with chronological training and test windows. Forward evaluation measures how predictions generalise to unseen games.

Goal Totals Prediction

Game totals (over/under) are predicted separately from the winner:

Expected Goals (xG) Model

Our shot-level xG model is a gradient-boosted classifier trained on individual shot events. It estimates the probability that each shot becomes a goal using features including:

The xG model is trained with strict temporal integrity — only shots from prior seasons are used for training — to prevent future data from leaking into historical metrics. See the xG Analysis page for team and player leaderboards.

Data Sources & Update Cadence

All data comes from the official NHL API. During the regular season and playoffs the pipeline runs daily to:

Transparency Commitment

We believe predictions without accountability are just noise. That's why we publish live performance metrics — including accuracy, Brier scores, calibration charts, and team-level breakdowns — updated with every site build. If the model is wrong, the data will show it.

For a broader introduction to the analytics concepts used here, see our NHL Analytics Guide.

Frequently Asked Questions

How are NHL game predictions made?

Each game prediction blends two machine-learning models — logistic regression and gradient-boosted classification — trained on thousands of historical NHL games. The models use rolling team stats, goalie performance, roster ratings, and rest days to produce a win probability for each team.

What data does the model use?

The model ingests game results, goalie stats, and shot-level data from the official NHL API. Features include 30-game rolling win percentages, goal differentials per game, recent goalie adjustments, roster ratings, and rest-day advantages. Data is updated daily during the NHL season.

Does the production model use calibration?

Production win probabilities use the raw model blend, without post-processing calibration.

How accurate are the predictions?

Accuracy depends on the model version and evaluation period. See the performance page for dated results and the accuracy guide for how to distinguish historical fits from forward tests.

Explore