CFB
›

CFB Betting Edge

2024 · Week 8 · SEC · backtest — what the model predicted vs what happened, and vs the market
AllSECBig TenBig 12ACCPac-12American AthleticMountain WestSun BeltMid-AmericanConference USAFBS Independents
Season202620252024
Week123456789101112131415
Week 8 backtest · SEC · 8 games — what the model predicted vs what happened
Straight up
4–450%
ATS vs close
5–363%
Model margin MAE
17.6
Market margin MAE
16.9
→ market was closer (model can't beat the close ATS)
Results — model read vs the final score + how the closing-line lean held up
Auburn @ MissouriFinal 17–21
Model
pred Missouri 12.3 · actual Missouri 4
winner Missouri ✓
ATS vs close
leaned Missouri -3.5Cover ✓
margin err: model 8.3 · mkt 0.5 · mkt closer
Georgia @ TexasFinal 30–15
Model
pred Texas 10.3 · actual Georgia 15
winner Texas ✗
ATS vs close
leaned Texas -4.0Miss ✗
margin err: model 25.3 · mkt 19.0 · mkt closer
South Carolina @ OklahomaFinal 35–9
Model
pred Oklahoma 10.2 · actual South Carolina 26
winner Oklahoma ✗
ATS vs close
leaned Oklahoma +1.0Miss ✗
margin err: model 36.2 · mkt 25.0 · mkt closer
Ball State @ VanderbiltFinal 14–24
Model
pred Vanderbilt 8.0 · actual Vanderbilt 10
winner Vanderbilt ✓
ATS vs close
leaned Ball State +27.5Cover ✓
margin err: model 2.0 · mkt 17.5 · closer
Kentucky @ FloridaFinal 20–48
Model
pred Kentucky 1.5 · actual Florida 28
winner Kentucky ✗
ATS vs close
leaned Florida +2.5Cover ✓
margin err: model 29.5 · mkt 30.5 · closer
Alabama @ TennesseeFinal 17–24
Model
pred Alabama 2.3 · actual Tennessee 7
winner Alabama ✗
ATS vs close
leaned Tennessee +3.5Cover ✓
margin err: model 9.3 · mkt 10.5 · closer
LSU @ ArkansasFinal 34–10
Model
pred LSU 6.2 · actual LSU 24
winner LSU ✓
ATS vs close
leaned LSU -3.0Cover ✓
margin err: model 17.8 · mkt 21.0 · closer
Texas A&M @ Mississippi StateFinal 34–24
Model
pred Texas A&M 22.3 · actual Texas A&M 10
winner Texas A&M ✓
ATS vs close
leaned Texas A&M -21.0Miss ✗
margin err: model 12.3 · mkt 11.0 · 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.