Zoltar is my NFL football prediction computer program. It uses a neural network and a form of reinforcement learning. Here are Zoltar’s predictions for week #10 of the 2026 season.

Zoltar:      giants  by    6  opp =  commanders    | Vegas:      giants  by  1.5
Zoltar:    patriots  by    3  opp =       lions    | Vegas:       lions  by  2.5
Zoltar:      chiefs  by    0  opp =     falcons    | Vegas:      chiefs  by  3.5
Zoltar:       bills  by   12  opp =        jets    | Vegas:       bills  by    7
Zoltar:       colts  by    4  opp =    dolphins    | Vegas:       colts  by  2.5
Zoltar:     packers  by    4  opp =     vikings    | Vegas:     packers  by    3
Zoltar:    panthers  by    0  opp =      saints    | Vegas:    panthers  by  1.5
Zoltar:     jaguars  by   12  opp =      titans    | Vegas:     jaguars  by  9.5
Zoltar:      texans  by    0  opp =      browns    | Vegas:      texans  by  4.5
Zoltar:    seahawks  by    5  opp =     raiders    | Vegas:    seahawks  by  3.5
Zoltar:        rams  by    4  opp =   cardinals    | Vegas:        rams  by  7.5
Zoltar: fortyniners  by    4  opp =     cowboys    | Vegas: fortyniners  by  4.5
Zoltar:    steelers  by    0  opp =     bengals    | Vegas:     bengals  by  3.5
Zoltar:      ravens  by    5  opp =    chargers    | Vegas:      ravens  by  3.5

Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I typically use a threshold of 4.5 points difference but in early and late parts of the season I use a more aggressive threshold of 3.0 or 3.5 points difference.

For week #10, using 4.5 points as the threshold, Zoltar likes one Vegas underdog and one Vegas favorite:

patriots     at        lions: Bet on Vegas underdog patriots
bills        at         jets: Bet on Vegas favorite  bills

A bet on the Vegas underdog Patriots against the Lions will pay off if the Patriots win by any score, or if the favored Lions win but by less than 2.5 points (i.e., 1 point or 2 points). If the 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 likely have changed. I’ve noticed that, compared to last year, point spreads are changing more dramatically by late Tuesdays than they used to. A swing of 7 points is not uncommon. Note that when I wrote this post, the Bills line was changing wildly.

I speculate that big point spread changes are 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.

This is the part of the season where injuries have a big effect on the point spread. Weeks 10 through 14 are usually Zoltar’s weakest.

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 #9, against the Vegas point spread, Zoltar went a poor 1-2 using 4.5 points as the advice threshold because. And sadly, the two games Zoltar missed on (underdog Ravens, underdog Eagles) were not close. Although the human-me would never have bet on these two games because the Ravens and Eagles starting QBs were out with injuries, and the backups were particularly weak.

For the season, against the spread, Zoltar is 15-8 (~65% 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 #9, just predicting the winning team, Zoltar went only 9-3 with 3 games to close to call, which is OK (75% correct). Vegas was incredible, going 14-1 at just predicting the winning team — the best result I can remember in recent memory.

My prediction system is math-based in the sense that it computes a numeric rating for each team and then uses ratings to compute the predicted margin of victory of the better team. An entirely different approach for predicting NFL football scores is to use a sophisticated simulation program and then simulate a game many thousands of times.

Right: “Half-Time Football” by Lakeside was produced in the late 1970s and early 80s. It’s strictly a dice game and is medium complexity.