Backtest History
285 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 | 3 | SEA @ MIN | 17–30 | +0.8 | +2.0 | -13.0 | 13.8 (model closer than the closing line) |
| 2021 | 3 | TB @ LA | 24–34 | -1.7 | +1.0 | -10.0 | 8.3 (model closer than the closing line) |
| 2021 | 3 | WAS @ BUF | 21–43 | -7.5 | -7.5 | -22.0 | 14.5 (model closer than the closing line) |
| 2021 | 2 | ATL @ TB | 25–48 | -12.1 | -13.5 | -23.0 | 10.9 |
| 2021 | 2 | BUF @ MIA | 35–0 | +1.1 | +3.5 | +35.0 | 33.9 |
| 2021 | 2 | CIN @ CHI | 17–20 | -0.3 | -2.0 | -3.0 | 2.7 |
| 2021 | 2 | DAL @ LAC | 20–17 | -2.6 | -3.0 | +3.0 | 5.6 (model closer than the closing line) |
| 2021 | 2 | DEN @ JAX | 23–13 | +7.7 | +6.0 | +10.0 | 2.3 (model closer than the closing line) |
| 2021 | 2 | DET @ GB | 17–35 | -7.9 | -11.5 | -18.0 | 10.1 |
| 2021 | 2 | HOU @ CLE | 21–31 | -10.1 | -13.5 | -10.0 | 0.1 (model closer than the closing line) |
| 2021 | 2 | KC @ BAL | 35–36 | +2.5 | +3.5 | -1.0 | 3.5 (model closer than the closing line) |
| 2021 | 2 | LA @ IND | 27–24 | +4.9 | +4.0 | +3.0 | 1.9 |
| 2021 | 2 | LV @ PIT | 26–17 | -3.9 | -5.5 | +9.0 | 12.9 (model closer than the closing line) |
| 2021 | 2 | MIN @ ARI | 33–34 | -5.7 | -4.0 | -1.0 | 4.7 |
| 2021 | 2 | NE @ NYJ | 25–6 | +5.4 | +5.5 | +19.0 | 13.6 |
| 2021 | 2 | NO @ CAR | 7–26 | +5.8 | +3.0 | -19.0 | 24.8 |
| 2021 | 2 | NYG @ WAS | 29–30 | -5.7 | -4.0 | -1.0 | 4.7 |
| 2021 | 2 | SF @ PHI | 17–11 | +1.6 | +3.0 | +6.0 | 4.4 |
| 2021 | 2 | TEN @ SEA | 33–30 | -9.8 | -6.5 | +3.0 | 12.8 |
| 2021 | 1 | ARI @ TEN | 38–13 | -5.4 | -2.5 | +25.0 | 30.4 |
| 2021 | 1 | BAL @ LV | 27–33 | +4.4 | +3.0 | -6.0 | 10.4 |
| 2021 | 1 | CHI @ LA | 14–34 | -9.7 | -9.5 | -20.0 | 10.3 (model closer than the closing line) |
| 2021 | 1 | CLE @ KC | 29–33 | -5.4 | -5.5 | -4.0 | 1.4 (model closer than the closing line) |
| 2021 | 1 | DAL @ TB | 29–31 | -10.1 | -10.0 | -2.0 | 8.1 |
| 2021 | 1 | DEN @ NYG | 27–13 | +3.0 | +3.0 | +14.0 | 11.0 (model closer than the closing line) |
| 2021 | 1 | GB vs NO | 3–38 | +5.9 | +4.0 | -35.0 | 40.9 |
| 2021 | 1 | JAX @ HOU | 21–37 | +1.8 | +3.5 | -16.0 | 17.8 (model closer than the closing line) |
| 2021 | 1 | LAC @ WAS | 20–16 | +2.8 | -2.5 | +4.0 | 1.2 (model closer than the closing line) |
| 2021 | 1 | MIA @ NE | 17–16 | -2.2 | -3.5 | +1.0 | 3.2 (model closer than the closing line) |
| 2021 | 1 | MIN @ CIN | 24–27 | +3.7 | +3.0 | -3.0 | 6.7 |
| 2021 | 1 | NYJ @ CAR | 14–19 | -2.4 | -3.5 | -5.0 | 2.6 |
| 2021 | 1 | PHI @ ATL | 32–6 | -5.1 | -3.5 | +26.0 | 31.1 |
| 2021 | 1 | PIT @ BUF | 23–16 | -7.7 | -6.5 | +7.0 | 14.7 |
| 2021 | 1 | SEA @ IND | 28–16 | +3.7 | +3.0 | +12.0 | 8.3 (model closer than the closing line) |
| 2021 | 1 | SF @ DET | 41–33 | +10.1 | +9.5 | +8.0 | 2.1 |
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.