Zoltar is my NFL football prediction computer program. It uses reinforcement learning and a neural network. Here are Zoltar's predictions for week #2 of the 2021 season. These predictions are tentative, in the sense that it usually takes Zoltar about three weeks to hit his stride.

Zoltar:    redskins  by    4  dog =      giants    Vegas:    redskins  by    3  Zoltar:      saints  by    0  dog =    panthers    Vegas:      saints  by  3.5  Zoltar:       bears  by    4  dog =     bengals    Vegas:       bears  by    3  Zoltar:      browns  by    6  dog =      texans    Vegas:      browns  by 12.5  Zoltar:       colts  by    2  dog =        rams    Vegas:        rams  by    4  Zoltar:     broncos  by    0  dog =     jaguars    Vegas:     broncos  by    6  Zoltar:    dolphins  by    2  dog =       bills    Vegas:       bills  by  3.5  Zoltar:    patriots  by    0  dog =        jets    Vegas:    patriots  by    6  Zoltar:      eagles  by    2  dog = fortyniners    Vegas: fortyniners  by  3.5  Zoltar:    steelers  by    6  dog =     raiders    Vegas:    steelers  by    6  Zoltar:   cardinals  by    6  dog =     vikings    Vegas:   cardinals  by  4.5  Zoltar:  buccaneers  by    6  dog =     falcons    Vegas:  buccaneers  by 12.5  Zoltar:    chargers  by    6  dog =     cowboys    Vegas:    chargers  by    3  Zoltar:    seahawks  by    6  dog =      titans    Vegas:    seahawks  by  5.5  Zoltar:      chiefs  by    0  dog =      ravens    Vegas:      chiefs  by    4  Zoltar:     packers  by    6  dog =       lions    Vegas:     packers  by 10.5

Zoltar theoretically suggests betting when the Vegas line is "significantly" different from Zoltar's prediction. In mid-season I 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.

At the beginning of the season, because of Zoltar's initialization (all teams regress to an average power rating) and other algorithms, Zoltar is very strongly biased towards Vegas underdogs. I need to fix this.

1. Zoltar likes Vegs underdog Texans against the Browns.
2. Zoltar likes Vegs underdog Colts against the Rams.
3. Zoltar likes Vegs underdog Jaguars against the Broncos.
4. Zoltar likes Vegs underdog Dolphins against the Bills.
5. Zoltar likes Vegs underdog Jets against the Patriots.
6. Zoltar likes Vegs underdog Eagles against the 49ers.
7. Zoltar likes Vegs underdog Falcons against the Buccaneers.
8. Zoltar likes Vegs underdog Lions against the Packers.

For example, a bet on the underdog Texans against the Browns will pay off if the Texans win by any score, or if the favored Browns win but by less than 12.5 points (in other words, win by 12 points or fewer).

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 #1, against the Vegas point spread, Zoltar went 4-2 (using 4.0 points as the advice threshold). Zoltar was correct in recommending Vegas underdogs Lions (thanks to a late spread change plus the 49ers giving up 16 points in the final few minutes), Texans, Cardinals, Raiders. Zoltar was wrong in recommending underdogs Colts and Giants.

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 #1, just predicting the winning team, Zoltar went 8-8 which isn't very good but is typical of the first few weeks of the season. In week #1, just predicting the winning team, Vegas -- "the wisdom of the crowd" -- went 9-7.

Zoltar sometimes predicts a 0-point margin of victory. There are four such games in week #2. 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.


Zoltar uses machine learning rather than a crystal ball. Left: "The Wizard of Oz" (1933). Center: "Labyrinth" (1986). Right: "Harry Potter and the Prisoner of Azkaban" (2004).