Zoltar is my NFL football prediction computer program. It uses a neural network and a type of quasi-reinforcement learning. Here are Zoltar’s predictions for week #4 of the 2026 season. These predictions are a bit tentative, in the sense that it usually takes Zoltar about four full weeks to hit his stride.

Zoltar:    steelers  by    0  opp =      browns    | Vegas:    steelers  by  2.5
Zoltar:       colts  by    3  opp =  commanders    | Vegas:       colts  by    3
Zoltar:       bills  by    4  opp =    patriots    | Vegas:       bills  by  6.5
Zoltar:       bears  by   11  opp =        jets    | Vegas:       bears  by  3.5
Zoltar:     jaguars  by    3  opp =     bengals    | Vegas:     bengals  by  2.5
Zoltar:      texans  by    6  opp =     cowboys    | Vegas:      texans  by  2.5
Zoltar:      giants  by    6  opp =   cardinals    | Vegas:      giants  by  1.5
Zoltar:      eagles  by    2  opp =        rams    | Vegas:        rams  by  2.5
Zoltar:      ravens  by   10  opp =      titans    | Vegas:      ravens  by 11.5
Zoltar:     packers  by    0  opp =  buccaneers    | Vegas:     packers  by  3.5
Zoltar:     vikings  by    9  opp =    dolphins    | Vegas:     vikings  by 10.5
Zoltar:      chiefs  by    0  opp =     raiders    | Vegas:      chiefs  by  4.5
Zoltar:    seahawks  by    8  opp =    chargers    | Vegas:    seahawks  by  6.5
Zoltar: fortyniners  by    2  opp =     broncos    | Vegas: fortyniners  by  2.5
Zoltar:       lions  by    0  opp =    panthers    | Vegas:       lions  by  2.5
Zoltar:     falcons  by    0  opp =      saints    | Vegas:      saints  by    3

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In the first few weeks of the season, I typically use 3.5 points difference, then for the middle part of the season I use 4.5 points.

At the beginning of the season, because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is strongly biased towards Vegas underdogs. The favor-underdogs effect seems less pronounced this season, compared to previous seasons.

For week #4, using a 3.5-point difference threshold, Zoltar has five suggestions:

jets         at        bears: Bet on Vegas favorite bears
jaguars      at      bengals: Bet on Vegas underdog jaguars
cardinals    at       giants: Bet on Vegas favorite giants
rams         at       eagles: Bet on Vegas underdog eagles
chiefs       at      raiders: Bet on Vegas underdog raiders

As a human, I mostly agree with Zoltar except for the Chiefs-Raiders game where Zoltar likes the underdog Raiders but my human eye likes the favorite Chiefs.

A bet on the favorite Bears against the Jets will win only if the Bears win by more than 3.5 points. If the Jets win outright, or if the Bears win but by less than 3.5 points, the bet on the Bears loses. If the Lions win by exactly 3.5 points, the bet is a push — which of course is impossible and the reason by point spreads usually have a 0.5 factor.

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 take into account overhead and miscellaneous mistakes).

In week #3, against the Vegas point spread, using a 3.5-point threshold, Zoltar went a good 3-1. Zoltar’s only miss was liking the underdog Dolphins against the Chiefs — the Dolphins lost badly 35-13.

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 #3, just predicting the winning team, Zoltar went a good 9-3 (with four games to close to call). Vegas was 8-8 at just predicting winners in week #3 — a poor result.

Left: Electric football was invented in the late 1940s. This is a 1960s era version. My brother Roger and I played this game a lot. (I miss you and your spirit Roger). The game is still very popular today. Center: Strat-O-Matic football was introduced in 1968 and was intended for teen boys as well as adults. My best friend Rob Carroll showed me the game when we were in high school (I miss you and your spirit Rob). The statistics of the game fascinated me when I was young and probably influenced my love of mathematics. Right: The 3M Pro Football game was introduced in 1966 but is no longer manufactured. I’ve played it a few times and enjoyed.