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 |
|---|---|---|---|---|---|---|---|
| 2023 | 7 | ATL @ TB | 16–13 | -3.8 | -3.0 | +3.0 | 6.8 |
| 2023 | 7 | BUF @ NE | 25–29 | +11.3 | +7.5 | -4.0 | 15.3 |
| 2023 | 7 | CLE @ IND | 39–38 | +0.3 | +3.5 | +1.0 | 0.7 (model closer than the closing line) |
| 2023 | 7 | DET @ BAL | 6–38 | -0.1 | -3.0 | -32.0 | 31.9 |
| 2023 | 7 | GB @ DEN | 17–19 | -0.1 | -1.5 | -2.0 | 1.9 |
| 2023 | 7 | JAX @ NO | 31–24 | -1.8 | -2.5 | +7.0 | 8.8 (model closer than the closing line) |
| 2023 | 7 | LAC @ KC | 17–31 | -6.7 | -5.5 | -14.0 | 7.3 (model closer than the closing line) |
| 2023 | 7 | LV @ CHI | 12–30 | -0.8 | +2.5 | -18.0 | 17.2 (model closer than the closing line) |
| 2023 | 7 | MIA @ PHI | 17–31 | -1.6 | -3.0 | -14.0 | 12.4 |
| 2023 | 7 | PIT @ LA | 24–17 | -5.0 | -3.5 | +7.0 | 12.0 |
| 2023 | 7 | SF @ MIN | 17–22 | +9.7 | +7.0 | -5.0 | 14.7 |
| 2023 | 7 | WAS @ NYG | 7–14 | +3.3 | +3.0 | -7.0 | 10.3 |
| 2023 | 6 | ARI @ LA | 9–26 | -7.3 | -7.0 | -17.0 | 9.7 (model closer than the closing line) |
| 2023 | 6 | BAL vs TEN | 24–16 | +4.1 | +5.5 | +8.0 | 3.9 |
| 2023 | 6 | CAR @ MIA | 21–42 | -13.6 | -14.0 | -21.0 | 7.4 |
| 2023 | 6 | DAL @ LAC | 20–17 | +0.9 | +1.5 | +3.0 | 2.1 |
| 2023 | 6 | DEN @ KC | 8–19 | -14.1 | -10.5 | -11.0 | 3.1 |
| 2023 | 6 | DET @ TB | 20–6 | +3.6 | +3.0 | +14.0 | 10.4 (model closer than the closing line) |
| 2023 | 6 | IND @ JAX | 20–37 | -3.2 | -4.0 | -17.0 | 13.8 |
| 2023 | 6 | MIN @ CHI | 19–13 | +0.1 | +3.0 | +6.0 | 5.9 |
| 2023 | 6 | NE @ LV | 17–21 | -5.6 | -3.0 | -4.0 | 1.6 |
| 2023 | 6 | NO @ HOU | 13–20 | -0.4 | +2.0 | -7.0 | 6.6 (model closer than the closing line) |
| 2023 | 6 | NYG @ BUF | 9–14 | -18.7 | -15.5 | -5.0 | 13.7 |
| 2023 | 6 | PHI @ NYJ | 14–20 | +6.4 | +6.5 | -6.0 | 12.4 (model closer than the closing line) |
| 2023 | 6 | SEA @ CIN | 13–17 | -0.1 | -3.0 | -4.0 | 3.9 |
| 2023 | 6 | SF @ CLE | 17–19 | +14.0 | +9.5 | -2.0 | 16.0 |
| 2023 | 6 | WAS @ ATL | 24–16 | -2.6 | -1.5 | +8.0 | 10.6 |
| 2023 | 5 | BAL @ PIT | 10–17 | +7.4 | +4.5 | -7.0 | 14.4 |
| 2023 | 5 | CAR @ DET | 24–42 | -11.6 | -9.5 | -18.0 | 6.4 (model closer than the closing line) |
| 2023 | 5 | CHI @ WAS | 40–20 | -7.6 | -6.0 | +20.0 | 27.6 |
| 2023 | 5 | CIN @ ARI | 34–20 | -0.9 | +3.0 | +14.0 | 14.9 |
| 2023 | 5 | DAL @ SF | 10–42 | -3.8 | -3.5 | -32.0 | 28.2 (model closer than the closing line) |
| 2023 | 5 | GB @ LV | 13–17 | -1.7 | -1.0 | -4.0 | 2.3 (model closer than the closing line) |
| 2023 | 5 | HOU @ ATL | 19–21 | +3.2 | -2.5 | -2.0 | 5.2 |
| 2023 | 5 | JAX vs BUF | 25–20 | -8.8 | -5.5 | +5.0 | 13.8 |
| 2023 | 5 | KC @ MIN | 27–20 | +6.4 | +3.5 | +7.0 | 0.6 (model closer than the closing line) |
| 2023 | 5 | NO @ NE | 34–0 | -1.1 | -2.5 | +34.0 | 35.1 (model closer than the closing line) |
| 2023 | 5 | NYG @ MIA | 16–31 | -15.3 | -12.5 | -15.0 | 0.3 (model closer than the closing line) |
| 2023 | 5 | NYJ @ DEN | 31–21 | +0.3 | -2.5 | +10.0 | 9.7 (model closer than the closing line) |
| 2023 | 5 | PHI @ LA | 23–14 | +2.7 | +3.5 | +9.0 | 6.3 |
| 2023 | 5 | TEN @ IND | 16–23 | +0.7 | +2.5 | -7.0 | 7.7 (model closer than the closing line) |
| 2023 | 4 | ARI @ SF | 16–35 | -14.1 | -15.0 | -19.0 | 4.9 |
| 2023 | 4 | ATL vs JAX | 7–23 | -0.7 | -3.5 | -16.0 | 15.3 |
| 2023 | 4 | BAL @ CLE | 28–3 | +1.0 | +2.0 | +25.0 | 24.0 |
| 2023 | 4 | CIN @ TEN | 3–27 | +2.8 | +2.5 | -24.0 | 26.8 |
| 2023 | 4 | DEN @ CHI | 31–28 | +3.5 | +3.0 | +3.0 | 0.5 |
| 2023 | 4 | DET @ GB | 34–20 | +0.8 | +2.5 | +14.0 | 13.2 |
| 2023 | 4 | KC @ NYJ | 23–20 | +10.9 | +9.5 | +3.0 | 7.9 |
| 2023 | 4 | LA @ IND | 29–23 | +2.3 | +1.0 | +6.0 | 3.7 (model closer than the closing line) |
| 2023 | 4 | LV @ LAC | 17–24 | -13.2 | -7.0 | -7.0 | 6.2 |
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.