Model performance
How the models are tracking — records, CLV, and the +EV subset. CLV is the honest long-run judge.
Winners
281-218
56%
Totals
63-66
49%
Run line
7-6
54%
Avg CLV
0.0%
beat the close
Shop gain
+0.31%
best vs avg book (ML)
By model
| Model | Moneyline | ML CLV | Totals | Tot CLV | Run line | RL CLV |
|---|---|---|---|---|---|---|
| rules_v1 | 291-218 · 57.2% | 0.0% | 240-269 · 47.2% | — | 57-63 · 47.5% | — |
| model_v2 | 281-218 · 56.3% | 0.0% | — | — | — | — |
| totals_v2 | 0-0 | — | 63-66 · 48.8% | +0.156 | — | — |
| runline_v2 | 0-0 | — | — | — | 7-6 · 53.8% | 2.1% |
rules_v1 = baseline · model_v2 = moneyline model · totals_v2 = weather totals · runline_v2 = derived run line. CLV > 0 = beating the close (ML/RL in prob, totals in runs).
+EV picks — flagged plays only
the subset the betting card flags| Model | +EV picks | Record | Win% | Avg odds | P/L (u) | ROI | CLV |
|---|---|---|---|---|---|---|---|
| model_v2 | 160 | 87-73 | 54% | -112 | +2.15u | +1.3% | -0.1% |
| totals_v2 | 87 | 43-44 | 49% | -108 | -3.92u | -4.5% | +0.15 |
| runline_v2 | 6 | 3-3 | 50% | +107 | +0.20u | +3.4% | 3.4% |
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.