Model status
Every week, how the model's picks did: wins and losses, against the 52.4% that breaks even at standard prices. Every pick was published before the games and graded against the box score. The whole record.
61.8%
of 477 picks won · 295–182
Above the 52.4% that breaks even at standard prices.
+86.2
Units at −110
+18.1%
Return
295–182
Since Tue 20 Oct
61.8%
Week by week
Win rate; the line is the break-evenThe chart starts with the second week.
Is the confidence honest?
The chartThe model is overconfident: its picks win less often than the chance it gives them (by 7.9 points on average).
Since Tue 20 Oct: picks grouped by the chance the model gave them, against how often each group won. This week alone: overconfident by 7.9 points, on 477 picks.
| By stat | W–L | Won | Units |
|---|---|---|---|
| Points | 55–24 | 69.6% | +26.0 |
| Rebounds | 123–95 | 56.4% | +16.8 |
| Assists | 117–63 | 65.0% | +43.4 |
| Strong picks | 66–21 | 75.9% | +39.0 |
| Solid picks | 121–59 | 67.2% | +51.0 |
| Lean picks | 108–102 | 51.4% | −3.8 |
| Overs | 31–11 | 73.8% | +17.2 |
| Unders | 264–171 | 60.7% | +69.0 |
Best calls
The widest wins
Brandon MillerUnder 24.5 PTS · Fri 23 Oct
6
Jamal MurrayUnder 21.5 PTS · Thu 22 Oct
6
Anthony EdwardsUnder 29.5 PTS · Fri 23 Oct
15
Worst misses
The widest losses, in public too Jamal MurrayUnder 23.5 PTS · Sat 24 Oct
42
Anthony EdwardsUnder 27.5 PTS · Wed 21 Oct
45
Walker KesslerUnder 11.5 PTS · Wed 21 Oct
26
The automated bankrolls this week
All bankrollsVirtual bankrolls that bet the model's picks by themselves, before the games. Past results are no promise.