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 |
|---|---|---|---|---|---|---|---|
| 2023 | 3 | PHI @ TB | 25–11 | +4.3 | +6.0 | +14.0 | 9.7 |
| 2023 | 3 | PIT @ LV | 23–18 | -3.1 | -3.0 | +5.0 | 8.1 |
| 2023 | 3 | TEN @ CLE | 3–27 | -3.1 | -3.5 | -24.0 | 20.9 |
| 2023 | 2 | BAL @ CIN | 27–24 | -1.6 | -3.5 | +3.0 | 4.6 (model closer than the closing line) |
| 2023 | 2 | CHI @ TB | 17–27 | -4.4 | -2.5 | -10.0 | 5.6 (model closer than the closing line) |
| 2023 | 2 | CLE @ PIT | 22–26 | +4.5 | +2.5 | -4.0 | 8.5 |
| 2023 | 2 | GB @ ATL | 24–25 | +1.1 | -3.0 | -1.0 | 2.1 |
| 2023 | 2 | IND @ HOU | 31–20 | +2.7 | +1.0 | +11.0 | 8.3 (model closer than the closing line) |
| 2023 | 2 | KC @ JAX | 17–9 | +1.3 | +3.5 | +8.0 | 6.7 |
| 2023 | 2 | LAC @ TEN | 24–27 | +1.9 | +2.5 | -3.0 | 4.9 (model closer than the closing line) |
| 2023 | 2 | LV @ BUF | 10–38 | -5.4 | -7.5 | -28.0 | 22.6 |
| 2023 | 2 | MIA @ NE | 24–17 | +3.3 | +2.0 | +7.0 | 3.7 (model closer than the closing line) |
| 2023 | 2 | MIN @ PHI | 28–34 | -6.9 | -6.0 | -6.0 | 0.9 |
| 2023 | 2 | NO @ CAR | 20–17 | +3.4 | +3.0 | +3.0 | 0.4 |
| 2023 | 2 | NYG @ ARI | 31–28 | -1.1 | +5.0 | +3.0 | 4.1 |
| 2023 | 2 | NYJ @ DAL | 10–30 | -9.5 | -8.5 | -20.0 | 10.5 (model closer than the closing line) |
| 2023 | 2 | SEA @ DET | 37–31 | -7.0 | -4.5 | +6.0 | 13.0 |
| 2023 | 2 | SF @ LA | 30–23 | +5.7 | +7.5 | +7.0 | 1.3 |
| 2023 | 2 | WAS @ DEN | 35–33 | -3.7 | -4.0 | +2.0 | 5.7 (model closer than the closing line) |
| 2023 | 1 | ARI @ WAS | 16–20 | -6.0 | -7.0 | -4.0 | 2.0 (model closer than the closing line) |
| 2023 | 1 | BUF @ NYJ | 16–22 | +5.3 | +2.5 | -6.0 | 11.3 |
| 2023 | 1 | CAR @ ATL | 10–24 | -3.3 | -3.5 | -14.0 | 10.7 |
| 2023 | 1 | CIN @ CLE | 3–24 | +2.5 | +1.0 | -21.0 | 23.5 |
| 2023 | 1 | DAL @ NYG | 40–0 | +5.0 | +3.5 | +40.0 | 35.0 (model closer than the closing line) |
| 2023 | 1 | DET @ KC | 21–20 | -5.7 | -4.0 | +1.0 | 6.7 |
| 2023 | 1 | GB @ CHI | 38–20 | +1.9 | -1.0 | +18.0 | 16.1 (model closer than the closing line) |
| 2023 | 1 | HOU @ BAL | 9–25 | -9.5 | -9.5 | -16.0 | 6.5 |
| 2023 | 1 | JAX @ IND | 31–21 | +5.6 | +4.0 | +10.0 | 4.4 (model closer than the closing line) |
| 2023 | 1 | LA @ SEA | 30–13 | -3.0 | -4.5 | +17.0 | 20.0 (model closer than the closing line) |
| 2023 | 1 | LV @ DEN | 17–16 | +1.1 | -3.0 | +1.0 | 0.1 (model closer than the closing line) |
| 2023 | 1 | MIA @ LAC | 36–34 | -1.6 | -3.0 | +2.0 | 3.6 (model closer than the closing line) |
| 2023 | 1 | PHI @ NE | 25–20 | +5.6 | +3.5 | +5.0 | 0.6 (model closer than the closing line) |
| 2023 | 1 | SF @ PIT | 30–7 | +3.9 | +1.5 | +23.0 | 19.1 (model closer than the closing line) |
| 2023 | 1 | TB @ MIN | 20–17 | -7.2 | -4.0 | +3.0 | 10.2 |
| 2023 | 1 | TEN @ NO | 15–16 | -3.3 | -3.0 | -1.0 | 2.3 |
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.