NFL 2017 Week 21 (Super Bowl LII) Prediction – Zoltar Predicts Patriots by 7 Points over Eagles

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 #21 (Super Bowl LII) of the 2017 NFL season:

Zoltar:    patriots  by    7  dog =      eagles    Vegas:    patriots  by  5.5

Zoltar theoretically suggests betting when the Vegas line is more than 4.0 points different from Zoltar’s prediction (3.0 points difference for regular season). Zoltar agrees with the Vegas point spread to within 4.0 points, so Zoltar has no recommendations.

But if forced to give advice, Zoltar would say take the Patriots. From a totally non-computer perspective, I speculate that, because the Patriots are one of the two or three most hated teams in the NFL, a lot of wishful-thinking money is being placed on the Eagles. This drives the Vegas point spread artificially in favor of the Eagles and therefore the Patriots are even more attractive to bet on.

==

Zoltar went 0-0 against the Vegas point spread last week — Zoltar agreed with Vegas to within 4.0 points on the Patriots-Jaguars, and Eagles-Vikings games.

Just predicting winners last week, Zoltar went 2-0.

For the 2017 regular season, against the Vegas point spread, Zoltar finished a pretty good 51-32 (61% 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.

I tracked how well Zoltar, Bing Predicts, and the Vegas line do when just predicting which team will win. For the 2017 regular season plus playoff games so far, just predicting the winning team, Zoltar finished 186-80 (70% accuracy), Bing finished 174-92 (65% accuracy), and Vegas finished 168-90 (65% accuracy). The best humans are typically about 67% accurate predicting winners, so Zoltar is slightly better than the best human experts. Bing did OK too, essentially matching 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.


My system is named after the arcade fortune telling machine.

This entry was posted in Machine Learning, Zoltar. Bookmark the permalink.