Zoltar is my NFL prediction computer program. It uses a deep neural network and reinforcement learning. Here are Zoltar’s predictions for week #11 of the 2018 NFL season:

Zoltar:    seahawks  by    5  dog =     packers    Vegas:    seahawks  by  2.5
Zoltar:     falcons  by    4  dog =     cowboys    Vegas:     falcons  by  3.5
Zoltar:     vikings  by    0  dog =       bears    Vegas:       bears  by    3
Zoltar:      titans  by    1  dog =       colts    Vegas:       colts  by  2.5
Zoltar:    panthers  by    2  dog =       lions    Vegas:    panthers  by    4
Zoltar:      saints  by    6  dog =      eagles    Vegas:      saints  by    8
Zoltar:  buccaneers  by    0  dog =      giants    Vegas:      giants  by    1
Zoltar:      ravens  by    4  dog =     bengals    Vegas:      ravens  by  4.5
Zoltar:    redskins  by    6  dog =      texans    Vegas:      texans  by    3
Zoltar:   cardinals  by    6  dog =     raiders    Vegas:   cardinals  by    4
Zoltar:    chargers  by   10  dog =     broncos    Vegas:    chargers  by    7
Zoltar:    steelers  by    4  dog =     jaguars    Vegas:    steelers  by  5.5
Zoltar:        rams  by    1  dog =      chiefs    Vegas:        rams  by  2.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week #11 Zoltar agrees closely with Las Vegas and so Zoltar has only two hypothetical suggestions.

1. Zoltar likes the Vegas underdog Titans against the Colts. Zoltar thinks the Titans are 1 point better than the Colts but Vegas has the Colts as favorites by 2.5 points. A bet on the Titans will pay off if the Titans win outright or if the Colts win but by less than 2.5 points (in other words, 1 or 2 points).

2. Zoltar likes the Vegas underdog Redskins against the Texans. Zoltar thinks the Redskins are 6 points better than the Texans but Vegas has the Texans favored by 3.0 points. This delta of opinion of 9 points is very large for Zoltar, which often means there’s a key injury on one of the teams. I have an advanced version of Zoltar that takes injuries into account. I usually run advanced Zoltar on Wednesday or Thursday.

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 (not by how many points). This isn’t useful except for parlay betting.

Zoltar sometimes predicts a 0-point margin of victory. There are two such games in week #11: Vikings vs. Bears and Buccaneers vs. Giants. In the first four weeks of the season, Zoltar picks the home team to win. After week #4, Zoltar uses historical data for the current season (which usually, but not always, ends up in a prediction that the home team will win).

==

Zoltar didn’t do very well in week #10. Against the Vegas point spread, Zoltar was an even 3-3. For the season so far, against the Vegas spread Zoltar is 33-18 which is just under 65% accuracy.

Just predicting winners, Zoltar was a so-so 9-5. Vegas was about the same at 8-6. For the season, just predicting which team will win, Zoltar is 104-42 (approximately 71% accuracy) and Vegas is 100-44 (about 69% accuracy).

My system is named after the fortune teller machine you can find in arcades. That Zoltar is named after the machine that appeared in the 1988 movie “Big” starring Tom Hanks. And that Zoltar is named after “Zoltan”, a machine from the 1960s.