–
Vegas closing favorite, same games
0
longest streak · current 0
–
when we differed from Vegas
65.0%
backtest 2010–2025 · Vegas 66.5%
→
Against the spread and the total
The same honesty for the two other things the model produces. Our projected margin is compared with the closing spread and our projected total with the closing total, the side is fixed before kickoff, and pushes are excluded. Expect these to sit near 50%: the backtest (2010–2025) covered 49.9% of spreads and hit 50.8% of totals, which is what "no edge against the closing line" looks like. Shown because hiding it would be the wrong lesson from the win–loss record.
52.4%
break-even rate at standard −110 odds
A 17-game season is a small sample: over ~270 games the 95% margin on an accuracy figure is about ±6 points, so a season proves less than it looks. The
backtest over 4,146 games is the fairer test of the method; this page is the live, pre-kickoff record.
Accuracy by week
Straight-up hit rate. Lighter bar = a week still in progress. Hover a bar for the numbers.
Fills in after the first graded week.
Does confidence mean anything?
Stated confidence vs. how often the pick was right.
Fills in after the first graded week.
Hit rate by confidence × week
Darker = the model was right more often. A healthy board is dark at the top, lighter at the bottom, in every column.
Fills in after the first graded week.
Week by week
Click a week for its picks.
| Week | Games | Correct | Rate | Vegas favorite |
|---|
| Week 1 | 14 | – | pending | – |
| Week 2 | 15 | – | pending | – |