CFB Betting Edge
2025 · Week 10 · American Athletic · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Week 10 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
6–0100%
ATS vs close
3–350%
Model margin MAE
13.3
Market margin MAE
13.5
Results — model read vs the final score + how the closing-line lean held up
UAB @ UConnFinal 19–38
Model
pred UConn 14.2 · actual UConn 19
winner UConn ✓
ATS vs close
leaned UConn -10.5Cover ✓
margin err: model 4.8 · mkt 8.5 · closer
Tulane @ UTSAFinal 26–48
Model
pred UTSA 2.7 · actual UTSA 22
winner UTSA ✓
ATS vs close
leaned UTSA +6.0Cover ✓
margin err: model 19.3 · mkt 28.0 · closer
Navy @ North TexasFinal 17–31
Model
pred North Texas 2.0 · actual North Texas 14
winner North Texas ✓
ATS vs close
leaned Navy +6.5Miss ✗
margin err: model 12.0 · mkt 7.5 · mkt closer
East Carolina @ TempleFinal 45–14
Model
pred East Carolina 1.1 · actual East Carolina 31
winner East Carolina ✓
ATS vs close
leaned Temple +5.5Miss ✗
margin err: model 29.9 · mkt 25.5 · mkt closer
Army @ Air ForceFinal 20–17
Model
pred Army 5.3 · actual Army 3
winner Army ✓
ATS vs close
leaned Army -1.5Cover ✓
margin err: model 2.3 · mkt 1.5 · mkt closer
Memphis @ RiceFinal 38–14
Model
pred Memphis 12.7 · actual Memphis 24
winner Memphis ✓
ATS vs close
leaned Rice +14.0Miss ✗
margin err: model 11.3 · mkt 10.0 · 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.