Zoltar is my NFL football prediction computer program. It uses a neural network and a variation of reinforcement learning. Here are Zoltar’s predictions for week #2 of the 2023 season. These predictions are fuzzy, in the sense that it usually takes Zoltar about four weeks to hit his stride.
Zoltar: eagles by 6 dog = vikings Vegas: eagles by 7
Zoltar: falcons by 2 dog = packers Vegas: packers by 1
Zoltar: bills by 9 dog = raiders Vegas: bills by 9
Zoltar: bengals by 6 dog = ravens Vegas: bengals by 3.5
Zoltar: lions by 6 dog = seahawks Vegas: lions by 6
Zoltar: texans by 1 dog = colts Vegas: colts by 1
Zoltar: chiefs by 0 dog = jaguars Vegas: chiefs by 3
Zoltar: chargers by 0 dog = titans Vegas: chargers by 3
Zoltar: buccaneers by 9 dog = bears Vegas: buccaneers by 3
Zoltar: giants by 1 dog = cardinals Vegas: giants by 4
Zoltar: fortyniners by 4 dog = rams Vegas: fortyniners by 8
Zoltar: cowboys by 6 dog = jets Vegas: cowboys by 3.5
Zoltar: commanders by 0 dog = broncos Vegas: broncos by 3.5
Zoltar: dolphins by 0 dog = patriots Vegas: dolphins by 2
Zoltar: saints by 0 dog = panthers Vegas: saints by 3
Zoltar: steelers by 4 dog = browns Vegas: browns by 2
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 point threshold:
bears at buccaneers : bet favorite buccaneers browns at steelers : bet underdog steelers
For week #2 using a liberal 2.5 point threshold:
packers at falcons : bet underdog falcons chiefs at jaguars : bet underdog jaguars chargers at titans : bet underdog titans bears at buccaneers : bet favorite buccaneers giants at cardinals : bet underdog cardinals fortyniners at rams : bet underdog rams commanders at broncos : bet underdog commanders saints at panthers : bet underdog panthers browns at steelers : bet underdog steelers
For example, a bet on the underdog Titans against the Chargers will pay off if the Titans win by any score, or if the favored Chargers win but by less than 3.0 points (in other words, by 2 points or less). If the Chargers win by exactly 3 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 liberal 3.0 point threshold, Zoltar went 6-6.
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 9-7 which isn’t very good but is typical of the first few weeks of the season. Just predicting which team will win, Vegas went 10-6.

My NFL prediction system is named after the Zoltar fortune teller machine you can find in arcades. Left: A Zoltar machine outside of Houdini’s Magic Shop in the New York New York hotel in Las Vegas. Unfortunately, that magic shop is gone now, a victim of the covid pandemic economic fallout. Center: Wagering on NFL games is a multi-billion dollar business. This is a photo of the sports book (betting area) at the MGM Grand hotel in Las Vegas. Right: This is a sheet where you can see the point spread for a given week. You can place a bet by going to a person at a desk in the sports book, or you can place a bet using a terminal or online.

.NET Test Automation Recipes
Software Testing
SciPy Programming Succinctly
Keras Succinctly
R Programming
2026 Visual Studio Live
2025 Summer MLADS Conference
2026 DevIntersection Conference
2025 Machine Learning Week
2025 Ai4 Conference
2026 G2E Conference
2026 iSC West Conference
You must be logged in to post a comment.