Zoltar is my NFL football prediction computer program. It uses a neural network and a type of reinforcement learning. Here are Zoltar’s predictions for week #18 (last regular season games) of the 2025 season, subject to the caution that teams with nothing to gain will bench many of their starting players.

Zoltar:  buccaneers  by    4  opp =    panthers    | Vegas:  buccaneers  by    3
Zoltar:    seahawks  by    0  opp = fortyniners    | Vegas:    seahawks  by    1
Zoltar:     falcons  by    6  opp =      saints    | Vegas:     falcons  by  2.5
Zoltar:     bengals  by    8  opp =      browns    | Vegas:     bengals  by  7.5
Zoltar:      texans  by    9  opp =       colts    | Vegas:      texans  by    9
Zoltar:     jaguars  by   12  opp =      titans    | Vegas:     jaguars  by   11
Zoltar:     vikings  by    4  opp =     packers    | Vegas:     vikings  by    7
Zoltar:     cowboys  by    3  opp =      giants    | Vegas:     cowboys  by  5.5
Zoltar:       bills  by   18  opp =        jets    | Vegas:       bills  by  7.5
Zoltar:       lions  by    0  opp =       bears    | Vegas:       bears  by  2.5
Zoltar:     broncos  by    6  opp =    chargers    | Vegas:     broncos  by    6
Zoltar:        rams  by   12  opp =   cardinals    | Vegas:        rams  by  9.5
Zoltar:      chiefs  by    7  opp =     raiders    | Vegas:      chiefs  by    4
Zoltar:    patriots  by    6  opp =    dolphins    | Vegas:    patriots  by  9.5
Zoltar:      eagles  by   11  opp =  commanders    | Vegas:      eagles  by  7.5
Zoltar:    steelers  by    3  opp =      ravens    | Vegas:      ravens  by  3.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. For this season I’ve been using a conservative threshold of 4 or 5 points difference in the early and late parts of the season, and a more aggressive threshold of 3 points in the middle of the season.

For week #18, using a threshold of 5 points, without taking the nothing-to-gain factor into account, Zoltar has only two suggestions:

jets         at        bills: Bet on Vegas favorite bills
ravens       at     steelers: Bet on Vegas underdog steelers 

For example, a bet on the underdog Steelers against the Ravens will pay off if the Steelers win by any score, or if the favored Ravens win but by less than 3.5 points (i.e., 3 points or less). 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 certainly have changed. Compared to previous years, point spreads are changing far 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.

At the end of the season, predictions get very dicey. Injuries have accumulated and teams that have nothing to gain often sit key players to avoid injuries.

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 logistics and things like data entry errors.

In week #17, Zoltar had his worst week in history. Against the Vegas point spread, Zoltar went 1-3 using 5.0 points as the advice threshold.

For the season, against the spread, Zoltar is 44-30 (~59% 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 #17, just predicting the winning team, Zoltar went 4-7 with 5 games too close for Zoltar to express an opinion. Terrible. Vegas was 6-10 at just predicting the winning team, which is also terrible. It was a tough week.

My football prediction system is named after the Zoltar fortune teller machine you can find in arcades. Fortune teller machines have been around for over 100 years.

Right: “Princess Doraldina” was made about 1928 by the Doraldina Fortune Telling Machine Company, of Rochester, New York. The machine dispensed a card with a fortune.