Model performance
How the models are tracking — records, CLV, and the +EV subset. CLV is the honest long-run judge.
Winners
—
Totals
—
Spread
10-10
50%
Avg CLV
-0.1%
beat the close
Shop gain
+0.14%
best vs avg book (ML)
By model
| Model | Moneyline | ML CLV | Totals | Tot CLV | Run line | RL CLV |
|---|---|---|---|---|---|---|
| cfb_elo | 14-7 · 66.7% | -0.1% | — | — | 10-10 · 50% | 0.1% |
cfb_elo = Elo — spread + ML · cfb_totals = weather totals. CLV > 0 = beating the close (all in win-prob).
+EV picks — flagged plays only
the subset the betting card flags| Model | +EV picks | Record | Win% | Avg odds | P/L (u) | ROI | CLV |
|---|---|---|---|---|---|---|---|
| cfb_elo | 18 | 10-8 | 56% | -102 | +1.72u | +9.6% | 0.2% |
Only the picks that cleared the +EV threshold. P/L is flat 1-unit stakes; avg odds is the mean price of those picks. Record, ROI, and P/L are outcome-based and noisy at this sample; CLV is the honest judge — does the model beat the close on the games it actually flags. Needs hundreds of picks to trust.