NCAAFModel 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

ModelMoneylineML CLVTotalsTot CLVRun lineRL CLV
cfb_elo14-7 · 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 picksRecordWin%Avg oddsP/L (u)ROICLV
cfb_elo1810-856%-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.