Every game since Oct 10, 2026, settled against the first line we captured (moneyline and run line). Simulated 1 unit a game, not real bets.
Moneyline
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.
1–1on the moneyline · since Oct 10
50.0%hit rate · break-even 55.3% at the prices taken
-0.3units at 1 a game · ROI -15.0%
1–0when the model disagreed by 5+ win-% points · +0.7 units
2 settled games: at this size the hit rate could be off by about
±69 points either way, far too few to separate skill from luck.
0 no action · 2 pending · 0 with no position (the model matched the market, or no price was posted).