NFL 2020 Week 7 Predictions – Zoltar Has Computer Covid - James D. McCaffreyJames D. McCaffrey

Zoltar is my NFL prediction computer program. It uses a deep neural network and reinforcement learning. Here are Zoltar’s predictions for week #7 of the chaotic covid-19 2020 NFL season:

Zoltar:      eagles  by    7  dog =      giants    Vegas:      eagles  by    6
Zoltar:     packers  by    3  dog =      texans    Vegas:     packers  by  3.5
Zoltar:       bills  by    5  dog =        jets    Vegas:       bills  by   11
Zoltar:      browns  by    3  dog =     bengals    Vegas:      browns  by  3.5
Zoltar:     cowboys  by    0  dog =    redskins    Vegas:     cowboys  by    3
Zoltar:     falcons  by    6  dog =       lions    Vegas:     falcons  by    3
Zoltar:      saints  by   10  dog =    panthers    Vegas:      saints  by  7.5
Zoltar:      titans  by    2  dog =    steelers    Vegas:    steelers  by    2
Zoltar:    seahawks  by    4  dog =   cardinals    Vegas:    seahawks  by    3
Zoltar:      chiefs  by    4  dog =     broncos    Vegas:      chiefs  by  9.5
Zoltar:    patriots  by    2  dog = fortyniners    Vegas:    patriots  by    3
Zoltar:    chargers  by    4  dog =     jaguars    Vegas:    chargers  by    8
Zoltar:     raiders  by    2  dog =  buccaneers    Vegas:  buccaneers  by    3
Zoltar:        rams  by    2  dog =       bears    Vegas:        rams  by  5.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week #7 Zoltar has six hypothetical suggestions (but see Note below):

1. Underdog Jets against the Bills
2. Underdog Titans against the Steelers
3. Underdog Broncos against the Chiefs
4. Underdog Jaguars against the Chargers
5. Underdog Raiders against the Buccaneers
6. Underdog Bears against the Rams

Note: I am convinced that the covid situation has fundamentally changed the NFL by giving Vegas favorites a slight mathematical edge compared to previous years (or equivalently, removing the mathematical advantage that underdogs used to have). I haven’t updated Zoltar’s prediction model (I just don’t have time) and so Zoltar is picking all underdogs even when it doesn’t make any sense. Therefore, Zoltar’s predictions this season are basically just completely wrong are being made just to diagnose for next year.

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.

Just for fun, I track how well Zoltar does when just trying to predict just which team will win a game. This isn’t useful except for parlay betting.

Zoltar did so-so in week #6. Against the Vegas point spread, Zoltar was 3-2 which isn’t great. For the season, Zoltar is 21-16 (57%) against the spread. Just predicting winners, Zoltar was a poor 8-6 (I think — the schedule changed several times during the week and I don’t have complete confidence in my statistics computations).

Just picking winners, the Vegas line went 9-5 which is typical for Vegas.