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 #15 of the 2020 NFL season:

Zoltar:     raiders  by    5  dog =    chargers    Vegas:     raiders  by  3.5
Zoltar:       bills  by    5  dog =     broncos    Vegas:       bills  by  6.5
Zoltar:     packers  by    9  dog =    panthers    Vegas:     packers  by    9
Zoltar:       colts  by    5  dog =      texans    Vegas:       colts  by    7
Zoltar:      titans  by    5  dog =       lions    Vegas:      titans  by  8.5
Zoltar:     vikings  by    5  dog =       bears    Vegas:     vikings  by    3
Zoltar:    seahawks  by    1  dog =    redskins    Vegas:    seahawks  by    6
Zoltar:    dolphins  by    1  dog =    patriots    Vegas:    dolphins  by  2.5
Zoltar:      ravens  by   10  dog =     jaguars    Vegas:      ravens  by   13
Zoltar:  buccaneers  by    1  dog =     falcons    Vegas:  buccaneers  by    6
Zoltar: fortyniners  by    1  dog =     cowboys    Vegas: fortyniners  by  2.5
Zoltar:   cardinals  by    3  dog =      eagles    Vegas:   cardinals  by    6
Zoltar:        rams  by   10  dog =        jets    Vegas:        rams  by   17
Zoltar:      chiefs  by    1  dog =      saints    Vegas:      chiefs  by    4
Zoltar:      browns  by    1  dog =      giants    Vegas:      browns  by    4
Zoltar:    steelers  by    6  dog =     bengals    Vegas:    steelers  by   13

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 #15. However, Zoltar tentatively likes two Vegas underdogs: Washington (Redskins) against the Seahawks, and Falcons against the Buccaneers. Zoltar sort of likes underdogs Jets and Bengals, but those games are outside of Zoltar’s mathematical range.

Against the Vegas point spread last week, experimental Zoltar was 2-1, correctly liking the underdog Dolphins against the Chiefs, and underdog Bills against the Steelers. Zoltar missed by liking the underdog Vikings when the Buccaneers won 26-14 and covered the 6.5 point spread.

Last week, there was an amazing “bad beat” for people who wagered on the underdog Cleveland Browns against the Baltimore Ravens. The Vegas point spread was -3.5 points so a bet on the Browns would win even if the Browns lost, but by 3 points or less. The Browns were losing badly but then had a great comeback, scored two touchdowns late and were trailing by only 3 points. But there were only 2 seconds left in the game – so people who bet on the Browns had a winning bet – that is, until the Browns tried a crazy play, which backfired, and the Ravens scored a 2-point safety (the rarest scoring play in football) with no time remaining. The Browns went from losing by 3 points to losing by 5 points, and so they didn’t cover the 3.5 spread, and millions of dollars was lost by people who bet on the Browns. I could almost hear the screams across the country.

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 #14, just predicting the winning team, Zoltar was a decent 12-4. The Las Vegas point spread had a poor week going just 10-6 just predicting winners.

Left: My prediction system is named after the Zoltar fortune teller machine you can find in arcades. Zoltar uses a crystal ball to navigate through the unknown. Center: The bridge of the spaceship Cygnus from the Disney film “The Black Hole” (1979) with large navigation balls. Not a very good movie. Right: The bridge of the spaceship C-57D from “Forbidden Planet” (1956) with a navigation ball. One of the best science fiction movies of all time.