Zoltar is my NFL football prediction computer program. It uses a neural network and a form of reinforcement learning. Here are Zoltar’s predictions for week #8 of the 2026 season.

Zoltar:     packers  by    6  opp =    panthers    | Vegas:     packers  by  4.5
Zoltar:       bills  by    9  opp =      ravens    | Vegas:       bills  by  3.5
Zoltar:     bengals  by   10  opp =      titans    | Vegas:     bengals  by 10.5
Zoltar:     cowboys  by    6  opp =   cardinals    | Vegas:     cowboys  by  6.5
Zoltar:     vikings  by    0  opp =       lions    | Vegas:       lions  by  3.5
Zoltar:     jaguars  by   10  opp =       colts    | Vegas:     jaguars  by  7.5
Zoltar:     raiders  by    0  opp =        jets    | Vegas:        jets  by  1.5
Zoltar:    steelers  by    6  opp =      browns    | Vegas:    steelers  by  3.5
Zoltar:  buccaneers  by    1  opp =     falcons    | Vegas:  buccaneers  by  1.5
Zoltar:        rams  by    6  opp =    chargers    | Vegas:        rams  by  7.5
Zoltar:     broncos  by    8  opp =      chiefs    | Vegas:      chiefs  by  1.5
Zoltar:    patriots  by    5  opp =    dolphins    | Vegas:    patriots  by  7.5
Zoltar:      eagles  by    0  opp =  commanders    | Vegas:  commanders  by  4.5
Zoltar:    seahawks  by    6  opp =       bears    | Vegas:    seahawks  by  3.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I typically use 4.5 points difference. For the first few weeks of the season, I am a bit more aggressive and use 3.5 points difference as the advice threshold criterion.

For week #8 Zoltar, using a 4.5 point advice threshold, likes one Vegas underdog and one Vegas favorite:

ravens       at        bills: Bet on Vegas favorite bills
chiefs       at      broncos: Bet on Vegas underdog broncos

For example, a bet on the underdog Broncos against the Chiefs will pay off if the Broncos win by any score, or if the favored Chiefs win but by less than 1.5 points (in other words, by 1 point). If the favored team wins by exactly the point spread, the wager is a push. This is why point spreads often have a 0.5 added — called “the hook” — to eliminate pushes.

I use the early Vegas point spreads, usually posted on late Monday night, right after the Monday Night Football game. By the time you read this, the point spreads will likely have changed. I’ve noticed that, compared to last year, point spreads are changing more dramatically by late Tuesdays than they used to. A swing of 7 points is not uncommon. I speculate that this is due to a huge increase in betting. When a lot of money is bet on one team in a matchup, the bookmakers must make a huge change in the point spread to encourage betting on the other team. Bookmakers only make money when the betting amounts are close to equal on both teams.

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 #7, against the Vegas point spread, Zoltar went 0-0 because he had no suggestions using a 4.5-point advice threshold. (Zoltar did think that the underdog Eagles would hold the favored Cowboys to a 3-point win, but Zoltar did not know that the Eagles starting QB was out with a serious injury).

For the season, against the Vegas spread, Zoltar is 12-6 (~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 #7, just predicting the winning team, Zoltar went a terrible 7-6 (with 1 game too close to call). Vegas went 9-5 at just predicting the winning team.

My Zoltar system is named after the Zoltar fortune teller machine you can find in arcades. Halloween is coming up and here are three clever Zoltar-inspired do-it-yourself costumes.