Zoltar is my NFL football prediction computer program. Zoltar uses a neural network and a type of quasi-reinforcement learning. Here are Zoltar’s predictions for week #5 of the 2026 season.

Zoltar:     cowboys  by    6  opp =  buccaneers    | Vegas:     cowboys  by  9.5
Zoltar:     jaguars  by    3  opp =      eagles    | Vegas:     jaguars  by  3.5
Zoltar:     bengals  by    0  opp =    dolphins    | Vegas:     bengals  by  6.5
Zoltar:     vikings  by    4  opp =      saints    | Vegas:      saints  by  1.5
Zoltar:    patriots  by   11  opp =     raiders    | Vegas:    patriots  by  3.5
Zoltar:      browns  by    0  opp =        jets    | Vegas:        jets  by  1.5
Zoltar:      texans  by    4  opp =      titans    | Vegas:      texans  by  6.5
Zoltar:    steelers  by    6  opp =       colts    | Vegas:    steelers  by  2.5
Zoltar:  commanders  by    1  opp =      giants    | Vegas:  commanders  by  3.5
Zoltar:     broncos  by    2  opp =    chargers    | Vegas:     broncos  by  3.5
Zoltar:       lions  by    2  opp =   cardinals    | Vegas:       lions  by  4.5
Zoltar:       bears  by    0  opp =     packers    | Vegas:       bears  by  2.5
Zoltar:    seahawks  by    4  opp = fortyniners    | Vegas:    seahawks  by  3.5
Zoltar:     falcons  by    2  opp =      ravens    | Vegas:     falcons  by  1.5
Zoltar:        rams  by    1  opp =       bills    | Vegas:        rams  by  2.5 

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I typically use 3.5 points difference as the advice threshold.

At the beginning of the season, because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is very strongly biased towards Vegas underdogs. I probably need to look at this. But the favor-underdogs effect seems less pronounced this season.

For week #5, using a 3.5-point difference between Zoltar’s predictions and the Vegas point spread, Zoltar has three suggestions:

bengals      at   dolphins:   Bet on Vegas underdog dolphins
vikings      at     saints:   Bet on Vegas underdog vikings
raiders      at   patriots:   Bet on Vegas favorite patriots 

A bet on the Vegas underdog Dolphins against the Bengals will pay off if the Dolphins win by any score, or if the favored Bengals win but by less than 6.5 points (in other words, by 6 points or fewer).

If the favored Bengals win by exactly 6.5 points — which is impossible — all bets are a push. This is why Vegas point spreads often have a .5 (called the hook) — to prevent pushes.

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 logistical mistakes.

In week #4, against the Vegas point spread, Zoltar went an excellent 4-1 using 3.5 points as the advice threshold. For the season, not counting the first week, against the spread, Zoltar is 8-4 (~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 #4, just predicting the winning team, Zoltar went 8-3 with 5 games to close to call, which is OK but not great. Vegas was 10-6 at just predicting the winning team, which is typical.

My system is named after the Zoltar fortune teller machine you can find in arcades. Zoltar uses a crystal ball. There are lots of movies that feature crystal ball fortune tellers. Here are three of my favorites.

Right: In “Harry Potter and the Prisoner of Azkaban” (2004), wacky Sybil Trelawney is a not-so-competent Professor of Divination.