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. For example, I changed the definition of a rout-win from winning by 20+ points to winning by 22+ points.
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 #19 (division championships) of the 2020 NFL season:
Zoltar: packers by 5 dog = rams Vegas: packers by 6.5 Zoltar: bills by 5 dog = ravens Vegas: bills by 2.5 Zoltar: chiefs by 5 dog = browns Vegas: chiefs by 10 Zoltar: saints by 5 dog = buccaneers Vegas: saints by 3
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.
Zoltar mostly agrees with the Vegas point spreads in week #19. However, Zoltar seems to like the Cleveland Browns against the Kansas City Chiefs. Zoltar thinks the Chiefs will win, but not by more than the 10.0 Vegas point spread.
A bet on Cleveland will pay off if Cleveland wins by any score, or if the Chiefs win but by less than 10 points. If the Chiefs win by exactly 10 points, all bets are a push.
Against the Vegas point spread last week, experimental Zoltar was 1-0. Zoltar correctly liked the underdog Washington (Redskins) against the favored Tampa Bay Buccaneers. The point spread moved from Buccs -8.0 to -9.5 and the Buccaneers won, but only by 8 points (31-23).
For the regular 2020 season, Zoltar finished 43-28 (60.5% accuracy) against the Las Vegas point spread. This is a bit worse than most seasons.
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 #18, just predicting the winning team, Zoltar was 4-2. The Las Vegas point spread was also 4-2.
For the season, just predicting which team would win, Zoltar finished 175-80 (68.6% accuracy) and Las Vegas finished nearly the same at 173-82 (67.8% accuracy).
My NFL prediction system is named after the Zoltar fortune teller machine you can find in arcades. Coin operated fortune teller machines first appeared in he 1890s. Center: The “Mystic Ray” machine is from the 1930s. It actually wrote a fortune with a moving pen. Impressive technology. Right: The “Zodi” from the 1930s has a typewriter powered by air tubes that typed out a fortune.