Going in, our model had favored Cincinnati Bengals at 66% win probability, and the pick lost.
Out or doubtful: 4 Ravens.
PICK: CIN
TIER B
PICK LOSTATS ✗
BAL 34%
CIN 66%
Model confidence: CIN 66%
Our line: CIN -5.5
ODDS
SPREAD
CIN -3.5
MARKET SPREAD · MARKET AVG
CIN -5.5
OUR LINE
MISSED
VS SPREAD
MONEYLINE
CIN · OUR WIN PROBABILITY
66%
CIN · MARKET WIN PROBABILITY
61%
DIFFERENCE
+5%
SOURCE
BAL
CIN
CIN WIN %
Closing line
+145
-175
61.4%
TEAM COMPARISON2023 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 2
+0.215Net EPA / play-0.044
+0.066 (5)Offense EPA / play-0.010 (12)
-0.149 (2)Defense EPA / play+0.034 (28)
47.4% (3)Offense success %44.0% (10)
GAME NARRATIVE
CIN B-tier pick misses. BAL takes it.
MISSED
Model picked CIN but BAL won. Projected margin was 5.5, the model overestimated by 8.5 points.
INSTANT CLASSIC
The win probability swung past 50% 7 times. One of the wildest games of the week.
ATS MISS
Missed the spread by 6.5 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.