END OF 1ST+1COL
MIN
46-24-12
12
COL
55-16-11
Model ensemble · how the prediction is built
3 sub-models, blended.
Each sub-model uses a different rating substrate. Bayesian model averaging weights them by rolling Brier score so the ensemble inherits each model's strengths. Disagreement flags games where the sub-models don't see eye-to-eye — lower confidence, wider band.
50.0%
ensemble · COL favored
Elo Static
fallback · inputs missing
50.0%
P(COL win)
33%
weight
Goalie Starter
fallback · inputs missing
50.0%
P(COL win)
33%
weight
Xg Blend
fallback · inputs missing
50.0%
P(COL win)
33%
weight
Disagreement
0.00 pp
weighted σ across sub-models
Confidence
100% · high
maps from disagreement
Substrate count
0 / 3 active
ones with full inputs tonight
Weights are recalibrated nightly on a 90-day rolling window with strict point-in-time correctness — no model gets credit for a game it hasn't seen
Player projections
COL vs MIN.
Per-player stat projections built from a recency-weighted blend of the last ten games, season average, and matchup context. Confidence reflects sample size and stability — the top of each list is who to watch.
135
projections · 114 high confidence
Shots on goal
- Matt BoldyMIN4.2± 2.0high
- Nathan MacKinnonCOL3.8± 2.2high
- Joel Eriksson EkMIN3.3± 1.6high
Goals
- Matt BoldyMIN0.7± 0.8high
- Nathan MacKinnonCOL0.6± 0.7high
- Kirill KaprizovMIN0.5± 0.7high
Points
- Nathan MacKinnonCOL1.4± 1.3high
- Mats ZuccarelloMIN1.4± 0.9high
- Matt BoldyMIN1.3± 1.0high
Projections recompute every 30 minutes · prop lines plug in once sportsbook ingest lands
