CFB Betting Edge
2024 · Week 13 · 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 13 backtest · American Athletic · 6 games — what the model predicted vs what happened
Straight up
3–350%
ATS vs close
4–267%
Model margin MAE
18.1
Market margin MAE
16.8
Results — model read vs the final score + how the closing-line lean held up
Army @ Notre DameFinal 14–49
Model
pred Notre Dame 18.9 · actual Notre Dame 35
winner Notre Dame ✓
ATS vs close
leaned Notre Dame -14.5Cover ✓
margin err: model 16.1 · mkt 20.5 · closer
Temple @ UTSAFinal 27–51
Model
pred UTSA 18.0 · actual UTSA 24
winner UTSA ✓
ATS vs close
leaned UTSA -16.5Cover ✓
margin err: model 6.0 · mkt 7.5 · closer
Tulsa @ South FloridaFinal 30–63
Model
pred South Florida 10.8 · actual South Florida 33
winner South Florida ✓
ATS vs close
leaned Tulsa +17.0Miss ✗
margin err: model 22.2 · mkt 16.0 · mkt closer
Charlotte @ Florida AtlanticFinal 39–27
Model
pred Florida Atlantic 6.9 · actual Charlotte 12
winner Florida Atlantic ✗
ATS vs close
leaned Florida Atlantic +3.0Miss ✗
margin err: model 18.9 · mkt 9.0 · mkt closer
East Carolina @ North TexasFinal 40–28
Model
pred North Texas 1.1 · actual East Carolina 12
winner North Texas ✗
ATS vs close
leaned East Carolina +2.5Cover ✓
margin err: model 13.1 · mkt 14.5 · closer
Rice @ UABFinal 14–40
Model
pred Rice 6.3 · actual UAB 26
winner Rice ✗
ATS vs close
leaned UAB +7.0Cover ✓
margin err: model 32.3 · mkt 33.0 · 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.