CFB Betting Edge

2025 · Week 8 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
Week 8 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
5–183%
ATS vs close
4–267%
Model margin MAE
18.1
Market margin MAE
18.3
→ model's margins were closer than the market
Results — model read vs the final score + how the closing-line lean held up
Model
pred South Florida 20.8 · actual South Florida 35
winner South Florida
ATS vs close
leaned South Florida -20.5Cover ✓
margin err: model 14.2 · mkt 14.5 · closer
Model
pred East Carolina 14.4 · actual East Carolina 14
winner East Carolina
ATS vs close
leaned Tulsa +16.5Cover ✓
margin err: model 0.4 · mkt 2.5 · closer
Army @ TulaneFinal 1724
Model
pred Tulane 3.6 · actual Tulane 7
winner Tulane
ATS vs close
leaned Army +10.0Cover ✓
margin err: model 3.4 · mkt 3.0 · mkt closer
UTSA @ North TexasFinal 1755
Model
pred North Texas 0.1 · actual North Texas 38
winner North Texas
ATS vs close
leaned UTSA +4.0Miss ✗
margin err: model 37.9 · mkt 34.0 · mkt closer
Temple @ CharlotteFinal 4914
Model
pred Temple 4.8 · actual Temple 35
winner Temple
ATS vs close
leaned Charlotte +9.5Miss ✗
margin err: model 30.2 · mkt 25.5 · mkt closer
Memphis @ UABFinal 2431
Model
pred Memphis 15.8 · actual UAB 7
winner Memphis
ATS vs close
leaned UAB +23.5Cover ✓
margin err: model 22.8 · mkt 30.5 · 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.