## NFL 2021 Week 9 Predictions – Zoltar Likes Jets, Jaguars, Saints

Zoltar is my NFL football prediction computer program. It uses reinforcement learning and a neural network. Here are Zoltar’s predictions for week #9 of the 2021 season. It usually takes Zoltar about four weeks to hit his stride and takes humans about eight weeks to get up to speed, so weeks six through nine are usually Zoltar’s sweet spot.

```Zoltar:       colts  by    6  dog =        jets    Vegas:       colts  by 16.5
Zoltar:    patriots  by    0  dog =    panthers    Vegas:    patriots  by  2.5
Zoltar:      browns  by    0  dog =     bengals    Vegas:     bengals  by    3
Zoltar:     cowboys  by    6  dog =     broncos    Vegas:     cowboys  by  7.5
Zoltar:       bills  by    5  dog =     jaguars    Vegas:       bills  by 10.5
Zoltar:    dolphins  by    6  dog =      texans    Vegas:    dolphins  by    7
Zoltar:      saints  by    9  dog =     falcons    Vegas:      saints  by  5.5
Zoltar:     raiders  by    0  dog =      giants    Vegas:     raiders  by  2.5
Zoltar:      ravens  by    6  dog =     vikings    Vegas:      ravens  by    6
Zoltar:    chargers  by    0  dog =      eagles    Vegas:    chargers  by    3
Zoltar:     packers  by    0  dog =      chiefs    Vegas:      chiefs  by  2.5
Zoltar:   cardinals  by    0  dog = fortyniners    Vegas:   cardinals  by    3
Zoltar:        rams  by    4  dog =      titans    Vegas:        rams  by    4
Zoltar:    steelers  by    6  dog =       bears    Vegas:    steelers  by    5
```

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I usually use 3.0 points difference but for the first few weeks of the season I go a bit more conservative and use 4.0 points difference as the advice threshold criterion. In middle weeks I sometimes go ultra-aggressive and use a 1.0-point threshold.

Note: Because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is much too strongly biased towards Vegas underdogs. I need to fix this.

For week #9:

1. Zoltar likes Vegas underdog Jets against Colts
2. Zoltar likes Vegas underdog Jaguars against Bills
3. Zoltar likes Vegas favorite Saints over Falcons

For example, a bet on the underdog Jets against the Colts will pay off if the Jets win by any score, or if the favored Colts win but by less than the point spread of 16.5 points (in other words, by 14 points or less).

Theoretically, if you must bet \$110 to win \$100 (typical in Vegas) then you’ll make money if you predict at 53% accuracy or better. But realistically, you need to predict at 60% accuracy or better.

In week #8, against the Vegas point spread, Zoltar went 3-3 (using the standard 3.0 points as the advice threshold). Overall, for the season, Zoltar is 33-26 against the spread (just under 56%).

Just for fun, I track how well Zoltar does when just trying to predict just which team will win a game. This isn’t useful except for parlay betting. In week #8, just predicting the winning team, Zoltar went 8-7 which is very poor — a lot of upsets in week #8.

In week #8, just predicting the winning team, Vegas — “the wisdom of the crowd” — also went 8-7.

Zoltar sometimes predicts a 0-point margin of victory, which means the two teams are evenly matched. There are six such games in week #9. In those situations, to pick a winner (only so I can track raw number of correct predictions) in the first few weeks of the season, Zoltar picks the home team to win. After that, Zoltar uses his algorithms to pick a winner.

My system is named after the fortune teller machine you can find in arcades. Many movies of the 1930s featured seances with crystal balls. Center: Detective Charlie Chan (actor Warner Oland) in “The Black Camel (1931)”. Actor Bela Lugosi of “Dracula” fame is to the right. Right: “Charlie Chan at Treasure Island (1939)”. Creepy.”

This entry was posted in Zoltar. Bookmark the permalink.