NHL

Model record

Every game since Oct 10, 2026, settled against the first line we captured (moneyline and puck line). Simulated 1 unit a game, not real bets.

The model's side is the team it gives a better chance than the market does (bookmaker margin removed), so read the hit rate against the prices' break-even. Prices are DraftKings first. Pushes return the stake; postponed, cancelled games are no action.

10–6 on the moneyline · since Oct 10

62.5% hit rate · break-even 54.3% at the prices taken

+2.3 units at 1 a game · ROI +14.6%

5–2 when the model disagreed by 5+ win-% points · +1.1 units

16 settled games: at this size the hit rate could be off by about ±24 points either way, far too few to separate skill from luck.

0 no action · 2 pending · 2 with no position (the model matched the market, or no price was posted).

Model's side vs the price	Result	Units
Sun, Oct 11 →
CAR -218CAR 4, PHI 1	✓ won	+0.46
NYR -265VAN 2, NYR 6	✓ won	+0.38
SEA +180SEA 5, WSH 3	✓ won	+1.80
Sat, Oct 10 →
ANA -122ANA 4, CGY 2	✓ won	+0.82
VGK -162LAK 1, VGK 2	✓ won	+0.62
NYI +142TBL 5, NYI 3	✗ lost	-1.00
BUF -108UTA 4, BUF 1	✗ lost	-1.00
DET +164DET 0, MTL 1	✗ lost	-1.00
OTT -162NSH 2, OTT 3	✓ won	+0.62
PIT +150DAL 1, PIT 2	✓ won	+1.50
CBJ +105CBJ 3, STL 5	✗ lost	-1.00
COL -218TOR 6, COL 3	✗ lost	-1.00
MIN +114MIN 4, FLA 1	✓ won	+1.14
SJS +130EDM 3, SJS 1	✗ lost	-1.00
NJD -298VAN 1, NJD 4	✓ won	+0.34
BOS -148PHI 1, BOS 5	✓ won	+0.68

Moneyline