Zoltar is my NFL football machine learning prediction system. It’s a hybrid system that uses a custom reinforcement learning algorithm plus a neural network. Here are Zoltar’s predictions for week #17 of the 2017 NFL season:
Zoltar: lions by 5 dog = packers Vegas: lions by 7.5 Zoltar: vikings by 15 dog = bears Vegas: vikings by 12 Zoltar: texans by 0 dog = colts Vegas: colts by 1 Zoltar: ravens by 7 dog = bengals Vegas: ravens by 10 Zoltar: titans by 4 dog = jaguars Vegas: jaguars by 3.5 Zoltar: steelers by 18 dog = browns Vegas: steelers by 15 Zoltar: bills by 0 dog = dolphins Vegas: bills by 2.5 Zoltar: saints by 5 dog = buccaneers Vegas: saints by 7.5 Zoltar: eagles by 6 dog = cowboys Vegas: cowboys by 3 Zoltar: falcons by 4 dog = panthers Vegas: falcons by 3.5 Zoltar: redskins by 1 dog = giants Vegas: redskins by 3.5 Zoltar: patriots by 18 dog = jets Vegas: patriots by 16 Zoltar: raiders by 0 dog = chargers Vegas: chargers by 7 Zoltar: chiefs by 4 dog = broncos Vegas: broncos by 3 Zoltar: seahawks by 6 dog = cardinals Vegas: seahawks by 8 Zoltar: rams by 10 dog = fortyniners Vegas: rams by 5.5
Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. In previous years, Zoltar would typically have hypothetical suggestions for only two or three games per week. But this season Zoltar and the Las Vegas line have differed greatly, and so Zoltar has been recommending six to eight games per week. The difference this season is the unusually large number of injuries to key players, especially quarterbacks.
This week, Zoltar has five hypothetical suggestions — a bit more than the usual two or three of previous seasons.
1. Zoltar likes the Vegas underdog Titans against the Jaguars. Vegas has the Jaguars as a moderate favorite by 3.5 points, but Zoltar believes the Titans are 4 points better than the Jaguars. A bet on the Titans would pay off if the Titans win outright, or if the Jaguars win but by less than 3.5 points (in other words, 3 points or less).
2. Zoltar likes the Vegas underdog Eagles against the Cowboys.
3. Zoltar likes the Vegas underdog Raiders against the Chargers.
4. Zoltar likes the Vegas underdog Chiefs against the Broncos.
5. Zoltar likes the Vegas favorite Rams over the San Francisco 49ers. Vegas has the Rams as 5.5 points better than the 49ers but Zoltar thinks the Rams are 10 points better. A bet on the Rams will pay off only if the Rams win by more than 5.5 points (i.e., 6 or more points).
Zoltar had pretty good results last week. Against the Vegas spread, which is what Zoltar is designed to predict, Zoltar went 3-2. There as one push game — the Chargers beat the Jets by 7 points and the Vegas point spread was 7.0 points. (I have an Advanced Zoltar who takes injuries into account; Advanced Zoltar went 1-1 in week #15).
For the 2017 season so far, against the Vegas point spread, Zoltar is a pretty good 49-29 (62% accuracy). If you must bet $110 to win $100 (typical in Vegas) then you must theoretically predict with 53% or better accuracy to make money, but realistically you must predict at 60% or better accuracy.
Just for fun, I also track how well Zoltar does when only predicting which team will win. This isn’t really useful except for parlay betting. For week #16, Zoltar was a quite good 12-4 just predicting which team would win
For comparison purposes, I also track how well Bing Predicts and the Vegas line do when just predicting which team will win. In week #16, Bing was 12-4, and Vegas was 11-4 when just predicting winners.
For the 2017 season so far, just predicting the winning team, Zoltar is 168-72 (70.0% accuracy), Bing is 159-81 (66.3% accuracy), and Vegas is 153-79 (66.0% accuracy). The best humans are typically about 67% accurate predicting winners, so currently, Zoltar is better than the best human experts. Bing is doing OK too, being slightly better than Vegas.
Note: Some of my numbers could be off a bit because of some weirdness with games played outside the U.S. (London and Mexico) earlier this season.