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 #3 of the 2025 season. These predictions are fuzzy, in the sense that it usually takes Zoltar about four weeks to hit his stride.

Zoltar:       bills  by   10  opp =    dolphins    | Vegas:       bills  by  8.5
Zoltar:     falcons  by    0  opp =    panthers    | Vegas:    panthers  by  1.5
Zoltar:     packers  by    5  opp =      browns    | Vegas:     packers  by  5.5
Zoltar:      texans  by    0  opp =     jaguars    | Vegas:      texans  by  1.5
Zoltar:     vikings  by    6  opp =     bengals    | Vegas:     vikings  by  1.5
Zoltar:    steelers  by    1  opp =    patriots    | Vegas:    patriots  by  1.5
Zoltar:       colts  by    4  opp =      titans    | Vegas:      titans  by  1.5
Zoltar:      eagles  by    6  opp =        rams    | Vegas:      eagles  by  4.5
Zoltar:  buccaneers  by   10  opp =        jets    | Vegas:  buccaneers  by  7.5
Zoltar:  commanders  by   10  opp =     raiders    | Vegas:  commanders  by  7.5
Zoltar:    chargers  by    6  opp =     broncos    | Vegas:    chargers  by  1.5
Zoltar:    seahawks  by    9  opp =      saints    | Vegas:    seahawks  by  6.5
Zoltar:     cowboys  by    0  opp =       bears    | Vegas:       bears  by    3
Zoltar:   cardinals  by    0  opp = fortyniners    | Vegas: fortyniners  by  3.5
Zoltar:      chiefs  by    7  opp =      giants    | Vegas:      chiefs  by  6.5
Zoltar:       lions  by    0  opp =      ravens    | Vegas:      ravens  by 3.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I usually use 3.0 points difference as the threshold, but for the first few weeks of the season I am usually a bit more conservative and use 4.0 or 5.0 points difference as the advice threshold criterion.

For week #3, using a conservative 4.0 threshold (suggest if difference is strictly greater than 4.0 points) Zoltar likes two Vegas favorites and one underdog:

bengals      at      vikings: Bet on Vegas favorite vikings
colts        at       titans: Bet on Vegas underdog colts
broncos      at     chargers: Bet on Vegas favorite chargers

For example, a bet on the Vegas underdog Colts against the Titans will pay off if the Colts win by any score, or if the favored Titans win but by less than 1.5 points.

Using a more conservative 5.0 point threshold, Zoltar likes only the Vegas underdog Colts.

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 mistakes.

In week #2, using a very conservative 5.0 point threshold, Zoltar went 2-1 against the spread. Zoltar was correct in picking the favorite Lions and underdog Saints, but wrong in picking the favorite Vikings.

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 #2, just predicting the winning team, Zoltar went 9-4 (with 3 games picked even) which is OK but not great. Vegas was 10-6 at just picking winners.

My football prediction program is named after the Zoltar fortune teller machine you can find in arcades. Fortune teller machines have been around for over 100 years. The two machines on the right are from about 1926.