Final: Tampa Bay Buccaneers 20, Minnesota Vikings 17.
Going in, our model had favored Minnesota Vikings at 60% win probability, and the pick lost.
PICK: MIN
TIER C
PICK LOSTATS ✗
TB 40%
MIN 60%
Model confidence: MIN 60%
Our line: MIN -3.5
ODDS
SPREAD
MIN -4.0
MARKET SPREAD · MARKET AVG
MIN -3.5
OUR LINE
MISSED
VS SPREAD
MONEYLINE
MIN · OUR WIN PROBABILITY
60%
MIN · MARKET WIN PROBABILITY
65%
DIFFERENCE
-5%
SOURCE
TB
MIN
MIN WIN %
Closing line
+170
-205
65.1%
TEAM COMPARISON2023 SEASON · EFFICIENCY, SCORING, TENDENCIES · RANK IN PARENTHESES · FULL-SEASON NUMBERS, NOT AS OF WEEK 1
+0.007Net EPA / play-0.023
-0.017 (14)Offense EPA / play-0.041 (17)
-0.024 (18)Defense EPA / play-0.018 (20)
39.6% (27)Offense success %42.4% (13)
GAME NARRATIVE
MIN C-tier pick misses. TB takes it.
MISSED
Model picked MIN but TB won. Projected margin was 3.5, the model overestimated by 6.5 points.
INSTANT CLASSIC
The win probability swung past 50% 9 times. One of the wildest games of the week.
ATS MISS
Missed the spread by 7.0 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.