Final: Las Vegas Raiders 26, Pittsburgh Steelers 17.
Going in, our model had favored Pittsburgh Steelers at 60% win probability, and the pick lost.
Out or doubtful: 5 Raiders, 1 Steelers.
PICK: PIT
TIER B
PICK LOSTATS ✗
LV 40%
PIT 60%
Model confidence: PIT 60%
Our line: PIT -3.6
ODDS
SPREAD
PIT -5.5
MARKET SPREAD · MARKET AVG
PIT -3.6
OUR LINE
MISSED
VS SPREAD
MONEYLINE
PIT · OUR WIN PROBABILITY
60%
PIT · MARKET WIN PROBABILITY
68%
DIFFERENCE
-8%
SOURCE
LV
PIT
PIT WIN %
Closing line
+201
-228
68.1%
WIN % is each book’s odds as a win chance, with the book’s cut taken out. The card above is their average.
TEAM COMPARISON2021 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 2
-0.064Net EPA / play-0.090
-0.019 (20)Offense EPA / play-0.074 (25)
+0.045 (25)Defense EPA / play+0.016 (19)
44.9% (13)Offense success %39.1% (31)
GAME NARRATIVE
PIT B-tier pick misses. LV takes it.
MISSED
Model picked PIT but LV won. Projected margin was 3.6, the model overestimated by 12.6 points.
ATS MISS
Missed the spread by 14.5 points.
DRAMATIC
The win probability swung past 50% 1 time. A competitive game throughout.
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.