CFB Betting Edge

2024 · Week 12 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 12 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
4–267%
ATS vs close
4–267%
Model margin MAE
15.3
Market margin MAE
18.8
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
UAB @ MemphisFinal 1853
Model
pred Memphis 20.4 · actual Memphis 35
winner Memphis
ATS vs close
leaned Memphis -16.5Cover ✓
margin err: model 14.6 · mkt 18.5 · closer
Model
pred Florida Atlantic 0.9 · actual Temple 3
winner Florida Atlantic
ATS vs close
leaned Florida Atlantic +2.0Miss ✗
margin err: model 3.9 · mkt 1.0 · mkt closer
North Texas @ UTSAFinal 2748
Model
pred North Texas 1.6 · actual UTSA 21
winner North Texas
ATS vs close
leaned North Texas +1.5Miss ✗
margin err: model 22.6 · mkt 19.5 · mkt closer
Model
pred East Carolina 6.1 · actual East Carolina 7
winner East Carolina
ATS vs close
leaned Tulsa +16.5Cover ✓
margin err: model 0.9 · mkt 9.5 · closer
Model
pred South Florida 9.0 · actual South Florida 35
winner South Florida
ATS vs close
leaned South Florida +1.5Cover ✓
margin err: model 26.0 · mkt 36.5 · closer
Tulane @ NavyFinal 350
Model
pred Tulane 11.0 · actual Tulane 35
winner Tulane
ATS vs close
leaned Tulane -7.5Cover ✓
margin err: model 24.0 · mkt 27.5 · 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.