🏒 NHL Model v1 2026-10-15 · 11 games

📋 Model season record logged daily, graded on finals

No graded games yet — picks log each afternoon, record builds as finals come in.
BUF @ TORmodel: BUF 58%
Win prob (home)
42%
Vegas lines (DK)
ML: BUF -102 · TOR -118
Puck: BUF +1.5 (-245) · TOR -1.5 (+200)
O/U 6.5 (o -130 / u +110)
Cover −1.5
H 26% · A 34%
Goalies
Pekka Luukkonen (Likely) · Sergei Bobrovsky (Likely)
Drivers
xG diff +0.087 · goalie -0.28
NYI @ OTTmodel: OTT 52%
Win prob (home)
52%
Vegas lines (DK)
ML: NYI +136 · OTT -162
Puck: NYI +1.5 (-198) · OTT -1.5 (+164)
O/U 5.5 (o -108 / u -112)
Cover −1.5
H 32% · A 28%
Goalies
Semyon Varlamov (Confirmed) · Linus Ullmark (Confirmed)
Drivers
xG diff -0.029 · goalie -0.51
SEA @ TBLmodel: TBL 58%
Win prob (home)
58%
Vegas lines (DK)
ML: SEA +225 · TBL -278
Puck: SEA +1.5 (-112) · TBL -1.5 (-108)
O/U 6.5 (o +110 / u -130)
Cover −1.5
H 35% · A 25%
Goalies
Joey Daccord (Unconfirmed) · Andrei Vasilevskiy (Likely)
Drivers
xG diff -0.097 · goalie -0.60
VAN @ FLAmodel: FLA 64%
Win prob (home)
64%
Vegas lines (DK)
ML: VAN +240 · FLA -298
Puck: VAN +1.5 (-105) · FLA -1.5 (-115)
O/U 6.5 (o +110 / u -130)
Cover −1.5
H 39% · A 21%
Goalies
Leevi Merilainen (Confirmed) · Akira Schmid (Confirmed)
Drivers
xG diff -0.084 · goalie +0.24
NYR @ NJDmodel: NJD 52%
Win prob (home)
52%
Vegas lines (DK)
ML: NYR +110 · NJD -130
Puck: NYR +1.5 (-218) · NJD -1.5 (+180)
O/U 6.5 (o +114 / u -135)
Cover −1.5
H 32% · A 28%
Goalies
Dylan Garand (Confirmed) · Nico Daws (Likely)
Drivers
xG diff -0.048 · goalie -0.71
PHI @ DETmodel: DET 62%
Win prob (home)
62%
Vegas lines (DK)
ML: PHI +120 · DET -142
Puck: PHI +1.5 (-225) · DET -1.5 (+185)
O/U 5.5 (o -120 / u +100)
Cover −1.5
H 38% · A 22%
Goalies
Joseph Woll (Confirmed) · Daniil Tarasov (Confirmed)
Drivers
xG diff -0.074 · goalie +0.14
WPG @ CHImodel: WPG 55%
Win prob (home)
45%
Vegas lines (DK)
ML: WPG -125 · CHI +105
Puck: WPG -1.5 (+195) · CHI +1.5 (-238)
O/U 6.5 (o +110 / u -130)
Cover −1.5
H 28% · A 32%
Goalies
Stuart Skinner (Likely) · Spencer Knight (Confirmed)
Drivers
xG diff +0.066 · goalie -0.14
SJS @ NSHmodel: NSH 59%
Win prob (home)
59%
Vegas lines (DK)
ML: SJS +110 · NSH -130
Puck: SJS +1.5 (-218) · NSH -1.5 (+180)
O/U 6.5 (o +102 / u -122)
Cover −1.5
H 36% · A 24%
Goalies
Alex Nedeljkovic (Confirmed) · Juuse Saros (Likely)
Drivers
xG diff -0.027 · goalie +0.35
STL @ MINmodel: MIN 56%
Win prob (home)
56%
Vegas lines (DK)
ML: STL +120 · MIN -142
Puck: STL +1.5 (-218) · MIN -1.5 (+180)
O/U 5.5 (o -135 / u +114)
Cover −1.5
H 34% · A 26%
Goalies
TBD
Drivers
xG diff +0.005 · goalie +0.33
UTA @ EDMmodel: UTA 53%
Win prob (home)
47%
Vegas lines (DK)
ML: UTA -115 · EDM -105
Puck: UTA -1.5 (+220) · EDM +1.5 (-270)
O/U 6.5 (o -118 / u -102)
Cover −1.5
H 29% · A 31%
Goalies
Karel Vejmelka (Confirmed) · Devon Levi (Confirmed)
Drivers
xG diff +0.028 · goalie -0.38
CGY @ VGKmodel: VGK 64%
Win prob (home)
64%
Vegas lines (DK)
ML: CGY +230 · VGK -285
Puck: CGY +1.5 (-118) · VGK -1.5 (-102)
O/U 6.5 (o +105 / u -125)
Cover −1.5
H 39% · A 21%
Goalies
Dustin Wolf (Confirmed) · Carter Hart (Confirmed)
Drivers
xG diff -0.076 · goalie +0.37

💎 Value board model's confident disagreements with Vegas

💎 SEA@TBL away — model 42% vs DK +225 (30%) · gap 12%
💎 BUF@TOR away — model 58% vs DK -102 (48%) · gap 10%
💎 VAN@FLA away — model 36% vs DK +240 (28%) · gap 8%
💎 NYI@OTT away — model 48% vs DK +136 (41%) · gap 7%
💎 CGY@VGK away — model 36% vs DK +230 (29%) · gap 7%
💎 PHI@DET home — model 62% vs DK -142 (56%) · gap 6%
6 plays logged — record builds as finals come in.
Only games where our win prob beats DK's no-vig implied prob by 5+ pts, ranked by gap. Dogs and favorites both qualify — confidence is the size of the disagreement. Experimental until ~100 graded plays.
Methodology (honest version): P(home win) from 5v5 xG differential, goalie quality (goals saved above expected), back-to-back flags, and home ice — logistic, walk-forward fitted on 2022–26 (3,854 games, 56.6% accuracy vs 54.3% baseline). Puck line P(cover −1.5) = P(win) × empirical P(win by 2+ | win) — 40% of NHL games end exactly 1-0/2-1/etc., and empty-netters make 3-goal margins more common than 2-goal ones. Early-season xG is regressed 8 games toward last season; goalie numbers are shrunk hard in October. Totals are excluded — team xG rates failed to beat the league average in backtest. Model-vs-DK gaps are shown for information, not as bets.