CFB Betting Edge

2024 · Week 10 · ACC · backtest — what the model predicted vs what happened, and vs the market
Week 10 backtest · ACC · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
0–60%
Model margin MAE
19.9
Market margin MAE
15.6
→ 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 Clemson 15.4 · actual Louisville 12
winner Clemson
ATS vs close
leaned Clemson -11.0Miss ✗
margin err: model 27.4 · mkt 23.0 · mkt closer
Duke @ MiamiFinal 3153
Model
pred Miami 10.7 · actual Miami 22
winner Miami
ATS vs close
leaned Duke +21.0Miss ✗
margin err: model 11.3 · mkt 1.0 · mkt closer
Stanford @ NC StateFinal 2859
Model
pred NC State 8.7 · actual NC State 31
winner NC State
ATS vs close
leaned Stanford +9.5Miss ✗
margin err: model 22.3 · mkt 21.5 · mkt closer
Pittsburgh @ SMUFinal 2548
Model
pred SMU 5.5 · actual SMU 23
winner SMU
ATS vs close
leaned Pittsburgh +7.0Miss ✗
margin err: model 17.5 · mkt 16.0 · mkt closer
Model
pred North Carolina 1.3 · actual North Carolina 24
winner North Carolina
ATS vs close
leaned Florida State +2.5Miss ✗
margin err: model 22.7 · mkt 21.5 · mkt closer
Model
pred Virginia Tech 11.4 · actual Syracuse 7
winner Virginia Tech
ATS vs close
leaned Virginia Tech -3.5Miss ✗
margin err: model 18.4 · mkt 10.5 · 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.