Zoltar is my NFL football prediction computer program. It uses a neural network and a form of quasi-reinforcement learning. Here are Zoltar’s predictions for week #6 of the 2026 season.

Zoltar:     broncos  by    4  opp =    seahawks    | Vegas:    seahawks  by  2.5
Zoltar:     jaguars  by    5  opp =      texans    | Vegas:     jaguars  by  2.5
Zoltar:       bears  by    0  opp =     falcons    | Vegas:       bears  by  3.5
Zoltar:      ravens  by    0  opp =      browns    | Vegas:      ravens  by  4.5
Zoltar:       colts  by   10  opp =      titans    | Vegas:       colts  by  6.5
Zoltar:    patriots  by   13  opp =        jets    | Vegas:    patriots  by  7.5
Zoltar:      giants  by    5  opp =      saints    | Vegas:      saints  by  1.5
Zoltar:      eagles  by    6  opp =    panthers    | Vegas:      eagles  by  1.5
Zoltar:    steelers  by    0  opp =  buccaneers    | Vegas:    steelers  by  2.5
Zoltar:        rams  by   11  opp =   cardinals    | Vegas:        rams  by   13
Zoltar:      chiefs  by    6  opp =    chargers    | Vegas:      chiefs  by  8.5
Zoltar:       bills  by    5  opp =     raiders    | Vegas:       bills  by  5.5
Zoltar:     packers  by    6  opp =     cowboys    | Vegas:     packers  by  1.5
Zoltar: fortyniners  by   12  opp =  commanders    | Vegas: fortyniners  by  7.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In the first few weeks of the season I use 3.5 points difference. For the middle weeks I use a more conservative 4.5 points as the advice threshold criterion.

For week #6 Zoltar, using 4.5 points as the advice threshold, likes two Vegas underdogs and one favorite:

seahawks     at      broncos: Bet on Vegas underdog broncos
jets         at     patriots: Bet on Vegas favorite patriots
saints       at       giants: Bet on Vegas underdog giants

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

This is an interesting part of the season for Zoltar. Zoltar has enough data to start getting more accurate, but humans have a lot of information too, including injuries, team chemistry, and so on.

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 (to account for overhead and miscellaneous mistakes).

In week #5, against the Vegas point spread, Zoltar had a 2-1 record (using 3.5 points as the advice threshold).

For the season, against the spread, Zoltar is 10-5 (66% accuracy).

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 #5, just predicting the winning team, Zoltar went only 7-4 (with 3 no-call games). Vegas was better, going 8-6 at just predicting the winning team.

My system is named after the Zoltar fortune teller machine you can find in arcades. It was my birthday recently. Last year I got a mini Zoltar machine for a present. It’s about 12 inches tall. Zoltar’s booth lights up, his arms and mouth and head and eyes move while he talks, and he gives out a fortune card. Very nice!

My system is named after the Zoltar fortune teller machine you can find in arcades. Zoltar is manufactured by Characters Unlimited, Inc., in Boulder City, Nevada, about 30 miles south of Las Vegas. The company makes several variations, including Confucius and Old Pirate. You can even get a custom machine made with your own face. Zoltar machines have many options. A more or less standard Zoltar machine costs about $9000.