CFB Betting Edge

2024 · Week 10 · Big 12 · backtest — what the model predicted vs what happened, and vs the market
Week 10 backtest · Big 12 · 5 games — what the model predicted vs what happened
Straight up
1–420%
ATS vs close
1–325%
Model margin MAE
20.5
Market margin MAE
17.2
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Model
pred Iowa State 13.5 · actual Texas Tech 1
winner Iowa State
ATS vs close
model matched the close — no lean
margin err: model 14.5 · mkt 14.5 · tie
Model
pred Oklahoma State 4.3 · actual Arizona State 21
winner Oklahoma State
ATS vs close
leaned Oklahoma State +5.0Miss ✗
margin err: model 25.3 · mkt 16.0 · mkt closer
TCU @ BaylorFinal 3437
Model
pred Baylor 1.9 · actual Baylor 3
winner Baylor
ATS vs close
leaned TCU +2.5Miss ✗
margin err: model 1.1 · mkt 0.5 · mkt closer
Arizona @ UCFFinal 1256
Model
pred Arizona 3.5 · actual UCF 44
winner Arizona
ATS vs close
leaned Arizona +6.5Miss ✗
margin err: model 47.5 · mkt 37.5 · mkt closer
Model
pred Kansas State 9.1 · actual Houston 5
winner Kansas State
ATS vs close
leaned Houston +12.5Cover ✓
margin err: model 14.1 · mkt 17.5 · closer
The model beats SP+ but not the closing line (ATS ≈ break-even). “Model−Mkt” is the gap between our projected home margin and the market's implied margin — a read on disagreement, not a profitable edge. Upcoming games have no closing line yet, so the market number marked ~ is the consensus midpoint of the best posted spreads across books.