Backtest History
2761 graded games
Every graded prediction from the frozen walk-forward backtest, next to the closing spread and the final margin. Lines are quoted for the home team.
| Season | Wk | Matchup | Score | Model | Close | Result | Model err |
|---|---|---|---|---|---|---|---|
| 2021 | 19 | PIT @ KC | 21–42 | -16.3 | -13.0 | -21.0 | 4.7 (model closer than the closing line) |
| 2021 | 19 | SF @ DAL | 23–17 | -4.4 | -3.0 | +6.0 | 10.4 |
| 2021 | 18 | CAR @ TB | 17–41 | -14.3 | -11.0 | -24.0 | 9.7 (model closer than the closing line) |
| 2021 | 18 | CHI @ MIN | 17–31 | -3.3 | -3.5 | -14.0 | 10.7 |
| 2021 | 18 | CIN @ CLE | 16–21 | -4.8 | -6.5 | -5.0 | 0.2 (model closer than the closing line) |
| 2021 | 18 | DAL @ PHI | 51–26 | +4.4 | +6.5 | +25.0 | 20.6 |
| 2021 | 18 | GB @ DET | 30–37 | +8.7 | +4.0 | -7.0 | 15.7 |
| 2021 | 18 | IND @ JAX | 11–26 | +15.0 | +14.0 | -15.0 | 30.0 |
| 2021 | 18 | KC @ DEN | 28–24 | +12.3 | +11.5 | +4.0 | 8.3 |
| 2021 | 18 | LAC @ LV | 32–35 | +4.3 | +3.5 | -3.0 | 7.3 |
| 2021 | 18 | NE @ MIA | 24–33 | +6.6 | +6.0 | -9.0 | 15.6 |
| 2021 | 18 | NO @ ATL | 30–20 | +3.7 | +4.5 | +10.0 | 6.3 |
| 2021 | 18 | NYJ @ BUF | 10–27 | -16.8 | -16.0 | -17.0 | 0.2 (model closer than the closing line) |
| 2021 | 18 | PIT @ BAL | 16–13 | -5.4 | -3.0 | +3.0 | 8.4 |
| 2021 | 18 | SEA @ ARI | 38–30 | -2.8 | -5.5 | +8.0 | 10.8 (model closer than the closing line) |
| 2021 | 18 | SF @ LA | 27–24 | -0.2 | -3.0 | +3.0 | 3.2 (model closer than the closing line) |
| 2021 | 18 | TEN @ HOU | 28–25 | +8.7 | +10.5 | +3.0 | 5.7 (model closer than the closing line) |
| 2021 | 18 | WAS @ NYG | 22–7 | +3.7 | +6.0 | +15.0 | 11.3 |
| 2021 | 17 | ARI @ DAL | 25–22 | -8.2 | -6.5 | +3.0 | 11.2 |
| 2021 | 17 | ATL @ BUF | 15–29 | -14.7 | -14.0 | -14.0 | 0.7 |
| 2021 | 17 | CAR @ NO | 10–18 | -7.3 | -7.0 | -8.0 | 0.7 (model closer than the closing line) |
| 2021 | 17 | CLE @ PIT | 14–26 | +4.5 | +1.0 | -12.0 | 16.5 |
| 2021 | 17 | DEN @ LAC | 13–34 | -7.2 | -8.0 | -21.0 | 13.8 |
| 2021 | 17 | DET @ SEA | 29–51 | -9.0 | -8.5 | -22.0 | 13.0 (model closer than the closing line) |
| 2021 | 17 | HOU @ SF | 7–23 | -10.8 | -14.0 | -16.0 | 5.2 |
| 2021 | 17 | JAX @ NE | 10–50 | -17.2 | -17.5 | -40.0 | 22.8 |
| 2021 | 17 | KC @ CIN | 31–34 | +4.2 | +3.5 | -3.0 | 7.2 |
| 2021 | 17 | LA @ BAL | 20–19 | +5.9 | +7.0 | +1.0 | 4.9 (model closer than the closing line) |
| 2021 | 17 | LV @ IND | 23–20 | -11.7 | -8.5 | +3.0 | 14.7 |
| 2021 | 17 | MIA @ TEN | 3–34 | -0.9 | -3.0 | -31.0 | 30.1 |
| 2021 | 17 | MIN @ GB | 10–37 | -16.1 | -13.0 | -27.0 | 10.9 (model closer than the closing line) |
| 2021 | 17 | NYG @ CHI | 3–29 | -8.5 | -7.0 | -26.0 | 17.5 (model closer than the closing line) |
| 2021 | 17 | PHI @ WAS | 20–16 | +7.2 | +6.5 | +4.0 | 3.2 |
| 2021 | 17 | TB @ NYJ | 28–24 | +15.1 | +14.5 | +4.0 | 11.1 |
| 2021 | 16 | BAL @ CIN | 21–41 | -4.5 | -7.5 | -20.0 | 15.5 |
| 2021 | 16 | BUF @ NE | 33–21 | -2.3 | -1.0 | +12.0 | 14.3 |
| 2021 | 16 | CHI @ SEA | 25–24 | -6.9 | -7.0 | +1.0 | 7.9 (model closer than the closing line) |
| 2021 | 16 | CLE @ GB | 22–24 | -9.6 | -7.5 | -2.0 | 7.6 |
| 2021 | 16 | DEN @ LV | 13–17 | +1.2 | +1.0 | -4.0 | 5.2 |
| 2021 | 16 | DET @ ATL | 16–20 | -6.1 | -7.5 | -4.0 | 2.1 (model closer than the closing line) |
| 2021 | 16 | IND @ ARI | 22–16 | +0.4 | -3.0 | +6.0 | 5.6 (model closer than the closing line) |
| 2021 | 16 | JAX @ NYJ | 21–26 | -1.6 | -2.5 | -5.0 | 3.4 |
| 2021 | 16 | LA @ MIN | 30–23 | +2.1 | +3.5 | +7.0 | 4.9 |
| 2021 | 16 | LAC @ HOU | 29–41 | +12.3 | +13.5 | -12.0 | 24.3 (model closer than the closing line) |
| 2021 | 16 | MIA @ NO | 20–3 | +0.7 | +3.0 | +17.0 | 16.3 |
| 2021 | 16 | NYG @ PHI | 10–34 | -11.7 | -11.0 | -24.0 | 12.3 (model closer than the closing line) |
| 2021 | 16 | PIT @ KC | 10–36 | -13.2 | -10.5 | -26.0 | 12.8 (model closer than the closing line) |
| 2021 | 16 | SF @ TEN | 17–20 | +5.1 | +3.5 | -3.0 | 8.1 |
| 2021 | 16 | TB @ CAR | 32–6 | +10.3 | +11.5 | +26.0 | 15.7 |
| 2021 | 16 | WAS @ DAL | 14–56 | -9.8 | -10.5 | -42.0 | 32.2 |
Model and Close are home lines; Result is the final margin on the same axis. Model err is the absolute miss of the model's margin, shown green when the model was closer than the closing line.