Week 2 Model Picks

Week 1 results went 2-4 and lost 4.20 units. Here are the Week 2 bets and what The Model thinks. Starter QBR is one game old, so last week’s blowouts are yelling.

Our Bets

Spread bets this week are only the 4-point edges. Totals stay on the table below; we are not betting them. Parlays are back: three moneyline tickets from The Model’s best win picks. Favorites on the moneyline, never a cover.

Spreads (5 units)

  • 2 units on Jaguars +2.5 (-102). The Model has Jacksonville winning outright by 6.9. That is a 9.4-point disagreement with Denver -2.5, the biggest edge on the board. Trevor Lawrence’s Week 1 QBR is 93.4; Bo Nix’s is 8.3 after Kansas City went into Denver and won 31-10. That gap is loud. We are still on the number.
  • 1 unit on Giants +7 (-105). The Model has the Rams by 1.2, not 7.
  • 1 unit on Browns +8.5 (-112). The Model has Tampa Bay by 2.9, not 8.5.
  • 1 unit on Colts +6.5 (+100). The Model has Kansas City by 2.3. We faded Indianapolis last week and lost. This is a different number.

Parlays (1 unit each)

  • Jaguars ML (+124) / Bills ML (-230) / Chargers ML (-298). Pays +329.
  • Texans ML (-148) / Patriots ML (-225) / Eagles ML (-325). Pays +217.
  • Seahawks ML (-205) / Bears ML (-218) / Ravens ML (-395). Pays +172.

No Thursday spread bet. Detroit at Buffalo is BUF -4.5 and The Model has Buffalo by 4.2. Buffalo is on parlay 1 as a moneyline. Chicago covering -4.5 is off the spread card; Chicago to win is on parlay 3.

The Model

Same ensemble as Week 1: Ridge, LightGBM, XGBoost, and a small neural net, trained on 2013–2025, using team stats, EPA, and starter QBR. It is not a money printer. This is what the math nerds think will happen.

The QBR warning is the whole Week 2 story. With shrinkage off, one start is the current-season number. Jacksonville over Denver is partly “the last box score was insane.” If you are going to fade The Model this week, fade it there.

The Model picks for Week 2, 2026: per-model margin of victory, pick, DraftKings spread, edge, win probability, and moneyline for all 16 games

Two yellow cells this week: Falcons over Panthers, and Jaguars over Broncos. Those are the outright underdog calls. We are betting Jacksonville. Atlanta’s edge is 3.9, just under the 4-point line, so it stays on the board and off the card. The Giants, Browns, and Colts are “the favorite wins, just not by that many.”

Over/Under Picks

The totals model was about 50/50 in the backtest, and Week 1 went 5-11. We are showing the numbers and not betting them.

The Model over/under picks for Week 2, 2026: predicted team scores, model total, DraftKings total, and difference for all 16 games

Where we disagree with Vegas

  • JAX at DEN: DEN -2.5; model MOV -6.9. Jacksonville has the better pregame points differential (9.9 vs 2.4) and the screaming QBR gap. This is the spread bet and the plus-money leg on parlay 1.
  • NYG at LA: LA -7.0; model MOV +1.2. The Rams are better. Seven is a lot of points, and the Giants just beat Dallas.
  • CLE at TB: TB -8.5; model MOV +2.9. Tampa Bay is better. Eight and a half is a lot of points.
  • IND at KC: KC -6.5; model MOV +2.3. Kansas City is better. Six and a half is a lot of points after Indianapolis got dropped by 18.
  • CAR at ATL: CAR -2.5; model MOV +1.4. On the board, not on the card. Edge is 3.9.
  • MIN at CHI: CHI -4.5; model MOV +8.1. Chicago just scored 59. Spread is off the card; Bears ML is on parlay 3.

Remember, the best way to use this is as one input into your own thinking. The Model does not know who is hurt, who is holding out, or which Week 1 box score was a mirage.

These are our personal bets and opinions, not betting advice. Wager at your own risk and within your means.

Good luck everyone.

Leave a Reply

Your email address will not be published. Required fields are marked *