Zoltar is my NFL prediction computer program. It uses a deep neural network and reinforcement learning. The results for the first half of the season were completely crazy. The covid-19 pandemic has had a massive effect on the NFL. I switched Zoltar into experimental mode starting in week #8. I fiddled with five of Zoltar’s parameters:
Base rating pts for a win: 16 to 14
Rout definition: win by 20+ to win by 22+
Rout rating pts: 4 to 2
Underdog away win bonus pts: 4 to 2
Home field advantage: 3 pts to 2 pts
These changes made Zoltar more conservative with regards to his betting strategy.
To me, the most interesting parameter is the home field advantage. For decades, both humans and Zoltar have given 3 points to the home team. But with covid-19, you can argue that the home field advantage is dramatically greater (say 5 or 6 points or more), or dramatically smaller (say 0 or 1 point), or even negative. I won’t know until after the 2020 season is completed and I have enough data to analyze.
Using the experimental parameters, here are Zoltar’s predictions for week #16 of the 2020 NFL season:
Zoltar: saints by 5 dog = vikings Vegas: saints by 7 Zoltar: buccaneers by 2 dog = lions Vegas: buccaneers by 9 Zoltar: cardinals by 3 dog = fortyniners Vegas: cardinals by 4.5 Zoltar: dolphins by 1 dog = raiders Vegas: dolphins by 3 Zoltar: ravens by 8 dog = giants Vegas: ravens by 10 Zoltar: chiefs by 10 dog = falcons Vegas: chiefs by 10.5 Zoltar: redskins by 5 dog = panthers Vegas: redskins by 2 Zoltar: browns by 5 dog = jets Vegas: browns by 9.5 Zoltar: bears by 4 dog = jaguars Vegas: bears by 7.5 Zoltar: texans by 5 dog = bengals Vegas: texans by 9 Zoltar: steelers by 3 dog = colts Vegas: steelers by 2.5 Zoltar: broncos by 0 dog = chargers Vegas: chargers by 3 Zoltar: seahawks by 5 dog = rams Vegas: seahawks by 1.5 Zoltar: cowboys by 1 dog = eagles Vegas: eagles by 1.5 Zoltar: packers by 5 dog = titans Vegas: packers by 3 Zoltar: bills by 2 dog = patriots Vegas: bills by 7
Old Zoltar theoretically used to suggest betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. At this point, it’s beginning to look like an improved strategy will be something like bet on Vegas underdogs only if Zoltar and Vegas differ by more than 6 points, or bet on Vegas favorites if Zoltar and Vegas differ by more than 2 points. I’ll have to do an analysis after this season is over.
When you bet on an underdog, your bet pays off if the underdog wins by any score, or if the game is a tie, or if the favorite team wins but by more than the Vegas point spread. If the favorite team wins by exactly the point spread, the bet is a push. You lose your bet if the favorite wins by more than the Vegas point spread.
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.
Because experimental Zoltar is very conservative, he mostly agrees with the Vegas point spreads in week #16. However, Zoltar tentatively likes three Vegas underdogs: Lions against the Buccaneers, Jets against the Browns, and Patriots against the Bills. In each case, Zoltar thinks the Vegas favorite will win, but not by as much as the point spread (9.0, 9.5, 7.0 respectively).
Against the Vegas point spread last week, experimental Zoltar was 4-0, correctly liking underdogs Washington (Redskins), Falcons, Jets, and Bengals. The Jets and Bengals game was really outside of Zoltar’s parameters, but I’ll count those games anyway.
Last week, there was another “bad beat” for people who wagered on the underdog New Orleans Saints against the Kansas City Chiefs. A bet on the Saints would pay off if the Saints won by any score, or if the Chiefs won but by less than 3 points. A Saints player literally had a recovered Chiefs fumble in his hands, in the end zone, for a touchdown. But he let the ball wiggle away and the Saints got only 2 points instead of a sure 7 points, and then the Chiefs went on to win by a score of 32-29 – exactly 3 points, so all bets were a push. (Note: the early line was Chiefs -4.0 but the mid-week line was Chiefs -3.0 as I used in my story).
For fun, I track how well Zoltar and the Vegas point spreads do when just predicting which team will win (not by how much). In week #15, just predicting the winning team, Zoltar was a poor 11-5. The Las Vegas point spread was the same at 11-5 just predicting winners.
My system is named after the Zoltar fortune teller machine you can find in arcades. Left: I saw this Zoltar in Las Vegas when I was speaking at a conference. Center: “The Egyptian Fortune Teller” by Rudolf Ernst (1854-1932). Right: “The Fortune Teller” by Edouard Frederic Wilhelm Richter (1844-1913).