Going in, our model had favored Indianapolis Colts at 50% win probability, and the pick lost.
Out or doubtful: 1 Texans, 1 Colts.
PICK: IND
TIER C
PICK LOSTATS ✓
HOU 50%
IND 50%
Model confidence: IND 50%
Our line: IND +0.0
ODDS
SPREAD
IND +3.0
MARKET SPREAD · MARKET AVG
IND +0.0
OUR LINE
COVERED
VS SPREAD
MONEYLINE
IND · OUR WIN PROBABILITY
50%
IND · MARKET WIN PROBABILITY
41%
DIFFERENCE
+9%
SOURCE
HOU
IND
IND WIN %
Closing line
-155
+130
41.3%
TEAM COMPARISON2024 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 1
+0.015Net EPA / play-0.061
-0.050 (22)Offense EPA / play-0.057 (24)
-0.065 (5)Defense EPA / play+0.004 (13)
38.8% (31)Offense success %40.2% (28)
GAME NARRATIVE
IND C-tier pick misses. HOU takes it.
MISSED
Model picked IND but HOU won. Projected margin was 0.0, the model overestimated by 2.0 points.
INSTANT CLASSIC
The win probability swung past 50% 5 times. One of the wildest games of the week.
COVERED
This pick covered the spread by 1.0 points.
Every model misses. The edge comes from the aggregate, not any single game.
SITUATIONAL TRENDS
Historical splits, shown for context only. We tested them: picking the situations that beat break-even in training goes 770–760 (50.3%) out of sample, so they are not a betting signal and are not coloured like one.
Every stat on this page is free, and so is the model's pick for this game. Pro is the separate question of which games we would actually bet, and at what stake, plus player props, unit sizing, and the full profit-and-loss ledger.