The pickThe locked winner and its win probability. A priced game's number is built on the market's no-vig price; the model's own margin and total sit beside the market's below, as context.
backtest · not locked
Win chance
58%Tennessee TitansLean
No moneyline was priced into this call, so it is the model's own number.
Model marginThe model's own predicted margin beside the market's number. Context for reading the game: the model makes no spread pick.
TEN by 2.8market ATL by 2.5
Model totalThe model's own predicted total points beside the market's number. Context for reading the game: the model makes no over/under pick.
32.5 pointsmarket 35
Backtest, not locked: this game finished before the model ran on it; the calls were reconstructed from pre-game information.
Why the model calls itThe reasons behind the winner call, in plain sentences drawn from this page's numbers.
The model has Tennessee Titans at 58% to win, with the market at ATL by 2.5.
Quarterback: the pick was locked with Will Levis starting for Tennessee Titans, and the model prices that in.
Counterpoint: third downs and the red zone favours ATL. ATL third-down conversion ranks #13, TEN defends it at #16; the other way TEN #28 into ATL's #3. The pick still lands on TEN because it rests on the whole season's results and the market's price, not one area.
Rest: TEN has 7 more days since its last game (TEN 14d, ATL 7d).
Home field is with TEN, which supports the pick.
ContextThe model makes it TEN by 2.8 against a market ATL by 2.5: 5.3 points of daylight in TEN's favour. The model's total is 32.5 against a line of 35: 2.5 points below it.The model makes no spread or over/under pick: neither has shown an edge over the market in our backtests.
Matchup context: who has the advantageWhich team has the advantage in each area, and how clearly. Context for reading the game, not model inputs.
Model TEN by 2.8 · market ATL by 2.5
ⓘContext, not inputs. These areas show how the two sides match up so you can read the game. The model's call comes from the teams' overall ratings, the quarterback, rest, home field and weather, not from these tiles.
Passing game
ATL
Slight advantage
ATL passing ranks #22, TEN defends it at #30; the other way TEN #21 into ATL's #19.
Rushing game
=
Even
TEN rushing ranks #13, ATL defends it at #1; the other way ATL #27 into TEN's #13.
Third down & red zone
ATL
Slight advantage
ATL third-down conversion ranks #13, TEN defends it at #16; the other way TEN #28 into ATL's #3.
Big plays
=
Even
TEN explosive pass rate ranks #8, ATL defends it at #18; the other way ATL #17 into TEN's #14.
Pass protection & rush
=
Even
ATL sack rate ranks #22, TEN defends it at #14; the other way TEN #31 into ATL's #18.
Ball security
TEN
Slight advantage
TEN turnovers / game ranks #10, ATL defends it at #27; the other way ATL #26 into TEN's #31.
Form (last 5)
TEN
Slight advantage
TEN −4.0 per game over the last five, ATL −7.6.
Market
ATL
Slight advantage
Consensus has ATL by 2.5; the model says TEN by 2.8.
the market, for comparison
Where the lines sitWhere the market's number and the model's sit among every final margin and total in the league's history; the highlighted bars are the games that landed between the two.
3,893 NFL games since 2012
Marginmarket ATL by 2.5 · model TEN by 2.8
Mkt ATL 2.5
Model TEN 2.8
← ATL by 28tieTEN by 28 →
9.4% of NFL games land between the two numbers. Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 35 · model 32.5
Mkt 35
Model 32.5
20 pts4672 pts
5.5% of NFL games finish between 35 and 32.5. The league’s median total since 2012 is 45.
The model alone was backtested walk-forward (each game priced only from what came before it). Since the winner call started following the market, the calibration that counts is the record of locked picks on the results page. Margin and total are context, not picks. Model reads, not personalized advice. For information only, not betting advice. 21+ only. Gambling problem? Call or text 1-800-GAMBLER.
