MLBModel 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

ModelMoneylineML CLVTotalsTot CLVRun lineRL CLV
rules_v1291-218 · 57.2%0.0%240-269 · 47.2%57-63 · 47.5%
model_v2281-218 · 56.3%0.0%
totals_v20-063-66 · 48.8%+0.156
runline_v20-07-6 · 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 picksRecordWin%Avg oddsP/L (u)ROICLV
model_v216087-7354%-112+2.15u+1.3%-0.1%
totals_v28743-4449%-108-3.92u-4.5%+0.15
runline_v263-350%+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.