Zoltar is my NFL football prediction computer program. It uses custom reinforcement learning and a neural network. Here are Zoltar’s predictions for week #17 of the 2021 season. It usually takes Zoltar about four weeks to hit his stride and takes humans about eight weeks to get up to speed, so weeks six through nine are usually Zoltar’s sweet spot. After week nine, injuries start having a big effect.
Zoltar: bills by 7 dog = falcons Vegas: bills by 13.5 Zoltar: bears by 6 dog = giants Vegas: bears by 4 Zoltar: chiefs by 2 dog = bengals Vegas: chiefs by 4 Zoltar: colts by 6 dog = raiders Vegas: colts by 7.5 Zoltar: cowboys by 6 dog = cardinals Vegas: cowboys by 2.5 Zoltar: saints by 6 dog = panthers Vegas: saints by 7 Zoltar: patriots by 11 dog = jaguars Vegas: patriots by 15.5 Zoltar: buccaneers by 5 dog = jets Vegas: buccaneers by 11 Zoltar: titans by 6 dog = dolphins Vegas: titans by 3.5 Zoltar: eagles by 0 dog = redskins Vegas: eagles by 2.5 Zoltar: chargers by 6 dog = broncos Vegas: chargers by 6 Zoltar: fortyniners by 6 dog = texans Vegas: fortyniners by 15 Zoltar: rams by 0 dog = ravens Vegas: rams by 2.5 Zoltar: seahawks by 6 dog = lions Vegas: seahawks by 9.5 Zoltar: packers by 9 dog = vikings Vegas: packers by 7 Zoltar: steelers by 4 dog = browns Vegas: steelers by 1.5
Zoltar theoretically suggests betting when the Vegas line is “significantly” different from Zoltar’s prediction. In mid-season I usually use 3.0 points difference but for the first few weeks and last few weeks of the season I go a bit more conservative and use 4.0 points difference as the advice threshold criterion. In middle weeks I sometimes go ultra-aggressive and use a 1.0-point threshold.
Note: Because of Zoltar’s initialization (all teams regress to an average power rating) and other algorithms, Zoltar is much too strongly biased towards Vegas underdogs. I need to fix this.
For week #17:
1. Zoltar likes Vegas favorite Cowboys over the Cardinals.
2. Zoltar likes Vegas underdog Falcons against the Bills.
3. Zoltar likes Vegas underdog Jaguars against the Patriots.
4. Zoltar likes Vegas underdog Jets against the Buccaneers.
5. Zoltar likes Vegas underdog Texans against the 49ers.
6. Zoltar likes Vegas underdog Lions against the Seahawks.
For example, a bet on the underdog Falcons against the Bills will pay off if the Falcons win by any score, or if the favored Bills win but by less than the point spread of 13.5 points (in other words, by 13 points or less).
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 #16, against the Vegas point spread, Zoltar went 3-0 (using the standard 3.0 points as the advice threshold and just advice on favorites). Overall, for the season, Zoltar is 54-44 against the spread (~55%).
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 #16, just predicting the winning team, Zoltar went 10-6 which is about average.
In week #16, just predicting the winning team, Vegas — “the wisdom of the crowd” went 11-5, one game better than Zoltar.
Zoltar sometimes predicts a 0-point margin of victory, which means the two teams are evenly matched. There are two such games in week #17. In those situations, to pick a winner (only so I can track raw number of correct predictions) in the first few weeks of the season, Zoltar picks the home team to win. After that, Zoltar uses his algorithms to pick a winner.
My system is named after the Zoltar fortune teller machine you can find in arcades. Coin operated fortune teller machines have been around for over 100 years and have taken many different forms. Center: This is a Sega Astrodata machine from 1971. You enter the current date, place your palm on a fake reader device, and the machine prints a fortune. A very complex and fascinating machine. Right: This is an Egyptian Seeress machine. I couldn’t find much information about it, but it looks like it’s from the 1960s.