CFB Betting Edge
2024 · Week 10 · Conference USA · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCAmerican AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Week 10 backtest · Conference USA · 5 games — what the model predicted vs what happened
Straight up
3–260%
ATS vs close
2–340%
Model margin MAE
10.4
Market margin MAE
9.3
Results — model read vs the final score + how the closing-line lean held up
Kennesaw State @ Western KentuckyFinal 14–31
Model
pred Western Kentucky 23.2 · actual Western Kentucky 17
winner Western Kentucky ✓
ATS vs close
leaned Kennesaw State +23.5Cover ✓
margin err: model 6.2 · mkt 6.5 · closer
Jacksonville State @ LibertyFinal 31–21
Model
pred Liberty 5.3 · actual Jacksonville State 10
winner Liberty ✗
ATS vs close
leaned Liberty -2.5Miss ✗
margin err: model 15.3 · mkt 12.5 · mkt closer
New Mexico State @ Florida InternationalFinal 13–34
Model
pred Florida International 4.0 · actual Florida International 21
winner Florida International ✓
ATS vs close
leaned New Mexico State +7.0Miss ✗
margin err: model 17.0 · mkt 14.0 · mkt closer
Middle Tennessee @ UTEPFinal 20–13
Model
pred UTEP 2.9 · actual Middle Tennessee 7
winner UTEP ✗
ATS vs close
leaned UTEP -2.0Miss ✗
margin err: model 9.9 · mkt 9.0 · mkt closer
Louisiana Tech @ Sam HoustonFinal 3–9
Model
pred Sam Houston 2.3 · actual Sam Houston 6
winner Sam Houston ✓
ATS vs close
leaned Louisiana Tech +10.5Cover ✓
margin err: model 3.7 · mkt 4.5 · 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.