Going in, our model had favored Baltimore Ravens at 66% win probability, and the pick lost.
Out or doubtful: 1 Ravens, 2 Raiders.
PICK: BAL
TIER A
PICK LOSTATS ✗
BAL 66%
LV 34%
Model confidence: BAL 66%
Our line: BAL -5.5
ODDS
SPREAD
BAL -3.0
MARKET SPREAD · MARKET AVG
BAL -5.5
OUR LINE
MISSED
VS SPREAD
MONEYLINE
BAL · OUR WIN PROBABILITY
66%
BAL · MARKET WIN PROBABILITY
61%
DIFFERENCE
+5%
SOURCE
BAL
LV
BAL WIN %
Closing line
-167
+149
61.2%
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 1
-0.065Net EPA / play-0.064
+0.005 (19)Offense EPA / play-0.019 (20)
+0.070 (27)Defense EPA / play+0.045 (25)
46.4% (10)Offense success %44.9% (13)
GAME NARRATIVE
BAL A-tier pick misses. LV takes it.
MISSED
Model picked BAL but LV won. Projected margin was 5.5, the model overestimated by 11.5 points.
INSTANT CLASSIC
The win probability swung past 50% 6 times. One of the wildest games of the week.
ATS MISS
Missed the spread by 9.0 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.