CFB Betting Edge

2025 · Week 13 · Big 12 · backtest — what the model predicted vs what happened, and vs the market
Week 13 backtest · Big 12 · 7 games — what the model predicted vs what happened
Straight up
6–186%
ATS vs close
4–357%
Model margin MAE
12.4
Market margin MAE
13.0
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred UCF 16.7 · actual UCF 3
winner UCF
ATS vs close
leaned UCF -13.5Miss ✗
margin err: model 13.7 · mkt 10.5 · mkt closer
Kansas State @ UtahFinal 4751
Model
pred Utah 7.4 · actual Utah 4
winner Utah
ATS vs close
leaned Kansas State +17.5Cover ✓
margin err: model 3.4 · mkt 13.5 · closer
Kansas @ Iowa StateFinal 1438
Model
pred Iowa State 5.7 · actual Iowa State 24
winner Iowa State
ATS vs close
leaned Iowa State -3.5Cover ✓
margin err: model 18.3 · mkt 20.5 · closer
Baylor @ ArizonaFinal 1741
Model
pred Baylor 0.8 · actual Arizona 24
winner Baylor
ATS vs close
leaned Baylor +6.5Miss ✗
margin err: model 24.8 · mkt 17.5 · mkt closer
TCU @ HoustonFinal 1714
Model
pred TCU 2.4 · actual TCU 3
winner TCU
ATS vs close
leaned TCU -1.5Cover ✓
margin err: model 0.6 · mkt 1.5 · closer
BYU @ CincinnatiFinal 2614
Model
pred BYU 5.0 · actual BYU 12
winner BYU
ATS vs close
leaned BYU -2.5Cover ✓
margin err: model 7.0 · mkt 9.5 · closer
Model
pred Arizona State 5.7 · actual Arizona State 25
winner Arizona State
ATS vs close
leaned Colorado +7.0Miss ✗
margin err: model 19.3 · mkt 18.0 · mkt 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.