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 |
|---|---|---|---|---|---|---|---|
| 2017 | 3 | CLE @ IND | 28–31 | -1.6 | -1.0 | -3.0 | 1.4 (model closer than the closing line) |
| 2017 | 3 | DAL @ ARI | 28–17 | -0.2 | +3.0 | +11.0 | 11.2 |
| 2017 | 3 | DEN @ BUF | 16–26 | +4.2 | +3.5 | -10.0 | 14.2 |
| 2017 | 3 | HOU @ NE | 33–36 | -14.3 | -13.5 | -3.0 | 11.3 |
| 2017 | 3 | KC @ LAC | 24–10 | +3.4 | +3.0 | +14.0 | 10.6 (model closer than the closing line) |
| 2017 | 3 | LA @ SF | 41–39 | +5.5 | +3.0 | +2.0 | 3.5 |
| 2017 | 3 | MIA @ NYJ | 6–20 | +4.9 | +5.5 | -14.0 | 18.9 (model closer than the closing line) |
| 2017 | 3 | NO @ CAR | 34–13 | -8.3 | -5.5 | +21.0 | 29.3 |
| 2017 | 3 | NYG @ PHI | 24–27 | -6.7 | -5.0 | -3.0 | 3.7 |
| 2017 | 3 | LV @ WAS | 10–27 | +4.0 | +3.5 | -17.0 | 21.0 |
| 2017 | 3 | PIT @ CHI | 17–23 | +9.3 | +7.0 | -6.0 | 15.3 |
| 2017 | 3 | SEA @ TEN | 27–33 | -4.1 | -2.0 | -6.0 | 1.9 (model closer than the closing line) |
| 2017 | 3 | TB @ MIN | 17–34 | +3.4 | 0.0 | -17.0 | 20.4 |
| 2017 | 2 | ARI @ IND | 16–13 | +3.7 | +7.0 | +3.0 | 0.7 (model closer than the closing line) |
| 2017 | 2 | BUF @ CAR | 3–9 | -6.3 | -6.5 | -6.0 | 0.3 (model closer than the closing line) |
| 2017 | 2 | CHI @ TB | 7–29 | -8.2 | -7.0 | -22.0 | 13.8 (model closer than the closing line) |
| 2017 | 2 | CLE @ BAL | 10–24 | -9.3 | -7.5 | -14.0 | 4.7 (model closer than the closing line) |
| 2017 | 2 | DAL @ DEN | 17–42 | +1.1 | +2.5 | -25.0 | 26.1 (model closer than the closing line) |
| 2017 | 2 | DET @ NYG | 24–10 | -1.9 | -3.0 | +14.0 | 15.9 (model closer than the closing line) |
| 2017 | 2 | GB @ ATL | 23–34 | -3.7 | -3.5 | -11.0 | 7.3 (model closer than the closing line) |
| 2017 | 2 | HOU @ CIN | 13–9 | -5.5 | -5.5 | +4.0 | 9.5 |
| 2017 | 2 | MIA @ LAC | 19–17 | -4.3 | -3.5 | +2.0 | 6.3 |
| 2017 | 2 | MIN @ PIT | 9–26 | -7.6 | -8.5 | -17.0 | 9.4 |
| 2017 | 2 | NE @ NO | 36–20 | +3.3 | +5.5 | +16.0 | 12.7 |
| 2017 | 2 | NYJ @ LV | 20–45 | -12.3 | -14.0 | -25.0 | 12.7 |
| 2017 | 2 | PHI @ KC | 20–27 | -4.5 | -4.0 | -7.0 | 2.5 (model closer than the closing line) |
| 2017 | 2 | SF @ SEA | 9–12 | -11.8 | -13.5 | -3.0 | 8.8 (model closer than the closing line) |
| 2017 | 2 | TEN @ JAX | 37–16 | -3.2 | +1.0 | +21.0 | 24.2 |
| 2017 | 2 | WAS @ LA | 27–20 | -6.9 | -3.0 | +7.0 | 13.9 |
| 2017 | 1 | ARI @ DET | 23–35 | +1.4 | +2.5 | -12.0 | 13.4 (model closer than the closing line) |
| 2017 | 1 | ATL @ CHI | 23–17 | +11.2 | +6.5 | +6.0 | 5.2 |
| 2017 | 1 | BAL @ CIN | 20–0 | -4.8 | -2.5 | +20.0 | 24.8 |
| 2017 | 1 | CAR @ SF | 23–3 | +2.6 | +4.5 | +20.0 | 17.4 |
| 2017 | 1 | IND @ LA | 9–46 | +2.5 | -3.5 | -37.0 | 39.5 |
| 2017 | 1 | JAX @ HOU | 29–7 | -4.7 | -5.5 | +22.0 | 26.7 (model closer than the closing line) |
| 2017 | 1 | KC @ NE | 42–27 | -9.7 | -8.0 | +15.0 | 24.7 |
| 2017 | 1 | LAC @ DEN | 21–24 | -1.8 | -3.0 | -3.0 | 1.2 |
| 2017 | 1 | NO @ MIN | 19–29 | -1.4 | -3.0 | -10.0 | 8.6 |
| 2017 | 1 | NYG @ DAL | 3–19 | -7.7 | -6.0 | -16.0 | 8.3 (model closer than the closing line) |
| 2017 | 1 | NYJ @ BUF | 12–21 | -9.1 | -7.0 | -9.0 | 0.1 (model closer than the closing line) |
| 2017 | 1 | LV @ TEN | 26–16 | -1.8 | -2.5 | +10.0 | 11.8 (model closer than the closing line) |
| 2017 | 1 | PHI @ WAS | 30–17 | -2.4 | +2.0 | +13.0 | 15.4 |
| 2017 | 1 | PIT @ CLE | 21–18 | +11.1 | +10.0 | +3.0 | 8.1 |
| 2017 | 1 | SEA @ GB | 9–17 | -4.2 | -2.5 | -8.0 | 3.8 (model closer than the closing line) |
| 2016 | 21 | NE vs ATL | 34–28 | +0.1 | +3.0 | +6.0 | 5.9 |
| 2016 | 20 | GB @ ATL | 21–44 | -5.1 | -6.5 | -23.0 | 17.9 |
| 2016 | 20 | PIT @ NE | 17–36 | -4.5 | -5.5 | -19.0 | 14.5 |
| 2016 | 19 | GB @ DAL | 34–31 | -1.4 | -5.5 | +3.0 | 4.4 (model closer than the closing line) |
| 2016 | 19 | HOU @ NE | 16–34 | -14.5 | -16.0 | -18.0 | 3.5 |
| 2016 | 19 | PIT @ KC | 18–16 | -0.6 | -2.5 | +2.0 | 2.6 (model closer than the closing line) |
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.