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

Zoltar:     packers  by    2  opp =  commanders    | Vegas:     packers  by  1.5
Zoltar:     bengals  by    6  opp =     jaguars    | Vegas:     bengals  by  5.5
Zoltar:     cowboys  by    6  opp =      giants    | Vegas:     cowboys  by  4.5
Zoltar:       lions  by   11  opp =       bears    | Vegas:       lions  by  4.5
Zoltar:    dolphins  by    6  opp =    patriots    | Vegas:    dolphins  by  2.5
Zoltar: fortyniners  by    0  opp =      saints    | Vegas: fortyniners  by    7
Zoltar:       bills  by    5  opp =        jets    | Vegas:       bills  by  8.5
Zoltar:        rams  by    4  opp =      titans    | Vegas:        rams  by  5.5
Zoltar:    steelers  by    6  opp =    seahawks    | Vegas:    steelers  by  1.5
Zoltar:      ravens  by   11  opp =      browns    | Vegas:      ravens  by 12.5
Zoltar:     broncos  by    0  opp =       colts    | Vegas:     broncos  by  3.5
Zoltar:   cardinals  by    6  opp =    panthers    | Vegas:   cardinals  by  4.5
Zoltar:      chiefs  by    2  opp =      eagles    | Vegas:      chiefs  by  1.5
Zoltar:     vikings  by   10  opp =     falcons    | Vegas:     vikings  by  4.5
Zoltar:  buccaneers  by    0  opp =      texans    | Vegas:      texans  by  1.5
Zoltar:    chargers  by    4  opp =     raiders    | Vegas:    chargers  by    3

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

For week #2 using a conservative 4.0 points as threshold:

bears        at        lions: Bet on Vegas favorite lions
fortyniners  at       saints: Bet on Vegas underdog saints
seahawks     at     steelers: Bet on Vegas favorite steelers
falcons      at      vikings: Bet on Vegas favorite vikings

For example, a bet on the Vegas underdog Saints against the 49ers will pay off if the Saints win by any score, or if the favored 49ers win but by less than the 7.0 point spread (in other words, by 6 points or less). If the 49ers win by exactly 7 points, the wager is a push.

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.

In week #1, against the Vegas point spread, using a 4.0 point threshold, Zoltar went 1-2. Zoltar correctly predicted that the favored Commanders would beat the Giants by more than the 6.0 Vegas point spread (the Commanders won 21-6). But Zoltar was wrong in predicting the 49ers would not cover their 2.5 points against the Seahawks (49ers won by 4 points, 17-13), and wrong in predicting Cardinals would not cover their 6.5 points against the Saints (the Cardinals won by 7 points, 20-13) — one point is the difference between going 2-1 against the spread and 1-2 against the spread. Grr.

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 #1, just predicting the winning team, Zoltar went 9-3 (with 4 games predicted even) which is pretty good but not great. For Las Vegas, just predicting which team will win, Vegas went 14-2, tied for the best result I can remember.

My NFL prediction system is named after the Zoltar fortune teller machine you can find in arcades.

Right: This is an old (from 2018) sheet where you can see the point spread for a given week. You would place a bet by going to a person at a desk in the sports book. This old style, of using paper and pencil and attendant, is rarely used anymore – replaced by online applications and kiosks.