Zoltar is my NFL football prediction computer program. It uses a neural network and a kind of quasi-reinforcement learning. Here are Zoltar’s predictions for week #11 of the 2025 season.

Zoltar:    patriots  by    8  opp =        jets    | Vegas:    patriots  by  5.5
Zoltar:  commanders  by    3  opp =    dolphins    | Vegas:  commanders  by  2.5
Zoltar:     vikings  by    6  opp =       bears    | Vegas:     vikings  by  2.5
Zoltar:      texans  by    5  opp =      titans    | Vegas:      texans  by    3
Zoltar:     falcons  by    4  opp =    panthers    | Vegas:     falcons  by    3
Zoltar:       bills  by    6  opp =  buccaneers    | Vegas:       bills  by  5.5
Zoltar:    chargers  by    3  opp =     jaguars    | Vegas:    chargers  by  1.5
Zoltar:     packers  by    5  opp =      giants    | Vegas:     packers  by  4.5
Zoltar:    steelers  by    6  opp =     bengals    | Vegas:     bengals  by  1.5
Zoltar:        rams  by    2  opp =    seahawks    | Vegas:        rams  by  4.5
Zoltar: fortyniners  by    0  opp =   cardinals    | Vegas: fortyniners  by  1.5
Zoltar:      chiefs  by    0  opp =     broncos    | Vegas:      chiefs  by  1.5
Zoltar:      ravens  by    5  opp =      browns    | Vegas:      ravens  by  8.5
Zoltar:      eagles  by    2  opp =       lions    | Vegas:      eagles  by  3.5
Zoltar:     cowboys  by    0  opp =     raiders    | Vegas:     cowboys  by  1.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. During the early and late parts of the season, I typically use a threshold of 4 points, and in the middle of the season I use a threshold of 3 points.

For week #11 Zoltar agrees closely with Las Vegas. Zoltar likes two Vegas underdogs and one favorite:

bears        at      vikings: Bet on Vegas favorite vikings
bengals      at     steelers: Bet on Vegas underdog steelers
ravens       at       browns: Bet on Vegas underdog browns

A bet on the Vegas underdog Steelers against the Bengals will pay off if the Steelers win by any score, or if the favored Bengals win but by less than 1.5 points (i.e., 1 point). If a 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 almost certainly have changed. I’ve noticed that, compared to previous years, point spreads are changing more dramatically by late Tuesdays than they used to. A swing of 10 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 logistics and careless errors (data entry, etc.)

In week #10, against the Vegas point spread, Zoltar went 3-2 (using 3.0 points as the advice threshold). For the season, against the spread, Zoltar is 25-18 (58% 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 #10, just predicting the winning team, Zoltar went 8-4 (75% correct) with 2 games too close for Zoltar to call, which is OK but not great. Vegas went 8-6 at just predicting the winning team, which is typical for Vegas in late-mid season.

My system is named after the Zoltar fortune teller machine you can find in arcades. While browsing Internet images, I came across a very nice “Ask the Brain” fortune teller machine.

LifeFormations renamed itself to LF Studios in 2023. The company designs and manufactures wonderful animatronics. Their web site at lfstudios.com is fantastic. If LF Studios made “Ask the Brain”, it looks like they no longer do so.