Zoltar is my NFL football prediction computer program. It uses reinforcement learning and a neural network. Here are Zoltar's predictions for week #1 of the 2021 season. These predictions are tentative, in the sense that it usually takes Zoltar about three weeks to hit his stride.

Zoltar:  buccaneers  by    6  dog =     cowboys    Vegas:  buccaneers  by  7.5  Zoltar:     falcons  by    2  dog =      eagles    Vegas:     falcons  by  3.5  Zoltar:       bills  by    4  dog =    steelers    Vegas:       bills  by  6.5  Zoltar:    panthers  by    6  dog =        jets    Vegas:    panthers  by    5  Zoltar:     vikings  by    0  dog =     bengals    Vegas:     vikings  by    3  Zoltar:       colts  by    2  dog =    seahawks    Vegas:    seahawks  by  2.5  Zoltar:       lions  by    2  dog = fortyniners    Vegas: fortyniners  by  7.5  Zoltar:      texans  by    6  dog =     jaguars    Vegas:     jaguars  by    3  Zoltar:      titans  by    6  dog =   cardinals    Vegas:      titans  by   23  Zoltar:    redskins  by    3  dog =    chargers    Vegas:    chargers  by    1  Zoltar:      chiefs  by    6  dog =      browns    Vegas:      chiefs  by    6  Zoltar:      saints  by    2  dog =     packers    Vegas:      saints  by  4.5  Zoltar:    dolphins  by    0  dog =    patriots    Vegas:    patriots  by    3  Zoltar:      giants  by    4  dog =     broncos    Vegas:     broncos  by  2.5  Zoltar:        rams  by    5  dog =       bears    Vegas:        rams  by  7.5  Zoltar:      ravens  by    0  dog =     raiders    Vegas:      ravens  by  4.5  

Zoltar theoretically suggests betting when the Vegas line is "significantly" different from Zoltar's prediction. In mid-season I use 3.0 points difference. For this first week of the season, I went a bit more conservative and used 4.0 points difference or more as the advice criterion.

At the beginning of the season, because of Zoltar's initialization and other algorithms, Zoltar is strongly biased towards Vegas underdogs.

1. Zoltar likes Vegas underdog Colts against the Seahawks.
2. Zoltar likes Vegas underdog Lions against the 49ers.
3. Zoltar likes Vegas underdog Texans against the Jaguars.
4. Zoltar likes Vegas underdog Cardinals against the Titans.
5. Zoltar likes Vegas underdog Giants against the Broncos.
6. Zoltar likes Vegas underdog Raiders against the Ravens.

For example, a bet on the Vegas underdog Colts against the Seahawks will pay off if the Colts win by any score, or if the favored Seahawks win but by less than 2.5 points (in other words, win by 2 points or fewer, in other words, win by 1 point or 2 points).

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.

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. I'll post results next week.

Zoltar sometimes predicts a 0-point margin of victory. There are three such games in week #1 (Vikings-Bengals, Dolphins-Patriots, Ravens-Raiders). 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 (Bengals, Patriots, Raiders). After that, Zoltar uses his algorithms to pick a winner.



My system is named after the Zoltar fortune teller machine that you can find in arcades. Arcade Zoltar is named after the Zoltar machine that appeared in the 1988 movie "Big". I suspect that movie Zoltar was named after the 1960s arcade fortune teller machine Zoltan.