Zoltar is my NFL football prediction computer program. It uses a neural network and a type of reinforcement learning. Here is Zoltar’s prediction for week #22 (Super Bowl LIX) of the 2024 season.
Zoltar: eagles by 1 dog = chiefs Vegas: chiefs by 1.5
Zoltar’s prediction that the Eagles will win by 1 point is close to the Las Vegas point spread which has the Chiefs listed as favorites by 1.5 points.
Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. During the beginning and end of the season, I use a conservative threshold of 4.0 points difference. During the middle part of the season I use a more aggressive threshold of 3.0 points difference.
For Super Bowl LIX (week #22), because Zoltar agrees to within 2.5 points of the Vegas point spread, Zoltar has no wager recommendation. But if forced to make a suggestion, Zoltar would advise betting on the underdog Eagles.
A bet on the Eagles will pay off if the Eagles win by any score, or if the Chiefs win by less than 1.5 points (i.e., exactly 1 point). A bet on the chiefs will pay off only if the Chiefs win by 2 points or more.
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 #21, against the Vegas point spread, Zoltar went 1-0 because the Chiefs covered the 2-point Vegas spread (but just barely).
For the season, against the spread, pending the result of the Super Bowl, Zoltar is 47-27 (~63% 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 #21, just predicting the winning team, Zoltar went 2-0. Vegas also went 2-0 at just predicting the winning team.

I’m old enough to have seen every Super Bowl. Here are three that I especially remember.
Left: I watched Super Bowl I in 1967 at my home in Fullerton, California on our family’s Zenith TV set. The Green Bay Packers beat the Kansas City Chiefs 35-10. At that time the Super Bowl wasn’t a big event like it is now, but the game still attracted a lot of attention. The game was televised in color, which was relatively rare in 1967.
Center: I grew up in Southern California and was therefore a Los Angeles Rams fan in the 1960s. But I had to wait until 2000 to see the Rams beat the Tennessee Titans 23-16 in Super Bowl XXXIV. The game featured rookie Kurt Warner who was never even drafted, and a bunch of “.com” TV ads, and a final play where a Titan receiver was tackled on the one-yard line to save the game for the Rams.
Right: I saw Super Bowl XLII in 2008 when the huge underdog New York Giants beat the then-undefeated New England Patriots 17-14. I saw this game in Las Vegas on huge TV screens in an auditorium at the MGM Grand Hotel, with four work colleagues. The game featured an unbelievable “helmet catch”. It was incredibly exciting in every way.

.NET Test Automation Recipes
Software Testing
SciPy Programming Succinctly
Keras Succinctly
R Programming
Visual Studio Live
Microsoft MLADS Conference
DevIntersection Conference
Machine Learning Week
Ai4 Conference
G2E Conference
iSC West Conference
You must be logged in to post a comment.