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
57%Los Angeles ChargersLean
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.
LAC by 2.3market LAC by 3
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.
48.6 pointsmarket 50.5
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 Los Angeles Chargers at 57% to win, with the market at LAC by 3.
Quarterback: the pick was locked with Justin Herbert starting for Los Angeles Chargers, and the model prices that in.
Counterpoint: rushing favours MIA. MIA rushing ranks #5, LAC defends it at #18; the other way LAC #32 into MIA's #10. The pick still lands on LAC because it rests on the whole season's results and the market's price, not one area.
Form: MIA has the better last five games by 7.6 points a game (LAC -13.8, MIA -6.2).
Home field is with LAC, which supports the pick.
ContextThe model makes it LAC by 2.3 against a market LAC by 3: essentially the same number, so there is little difference to read. The model's total is 48.6 against a line of 50.5: 1.9 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 LAC by 2.3 · market LAC by 3
ⓘMost of these areas favor MIA, but the model still picks LAC. The model rates each team on its full body of results, adjusted for who it played, plus the quarterback, rest, home field and weather. Single-area matchups like these are shown for context: over past seasons, when they point the other way the winner has been close to a coin flip, so they have not been a better guide than the ratings.
Passing game
MIA
Clear advantage
MIA passing ranks #5, LAC defends it at #24; the other way LAC #17 into MIA's #15.
Rushing game
MIA
Clear advantage
MIA rushing ranks #5, LAC defends it at #18; the other way LAC #32 into MIA's #10.
Third down & red zone
=
Even
LAC red-zone touchdown rate ranks #14, MIA defends it at #26; the other way MIA #3 into LAC's #13.
Big plays
MIA
Clear advantage
MIA explosive rush rate ranks #1, LAC defends it at #10; the other way LAC #32 into MIA's #1.
Pass protection & rush
MIA
Clear advantage
MIA sack rate ranks #5, LAC defends it at #11; the other way LAC #12 into MIA's #1.
Ball security
MIA
Slight advantage
MIA turnovers / game ranks #24, LAC defends it at #22; the other way LAC #19 into MIA's #8.
Form (last 5)
MIA
Clear advantage
LAC −13.8 per game over the last five, MIA −6.2.
Market
LAC
Slight advantage
Consensus has LAC by 3; the model says LAC by 2.3.
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 LAC by 3 · model LAC by 2.3
Mkt LAC 3
Model LAC 2.3
← MIA by 28tieLAC by 28 →
No whole-number margin falls between 3 and 2.3, so the two numbers differ only on a push at 3. The market is on 3, a number 14.5% of games land on exactly (a push). Most common margins: 3 (14.5%), 7 (8.6%), 6 (6.7%), 14 (5.1%).
Totalmarket 50.5 · model 48.6
Mkt 50.5
Model 48.6
20 pts4672 pts
4.9% of NFL games finish between 50.5 and 48.6. 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.
