NFL 2016 Week 5 Predictions – Zoltar Likes Redskins and Panthers

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 5 of the 2016 NFL season:

Zoltar:   cardinals  by    4  dog = fortyniners    Vegas:   cardinals  by    3
Zoltar:       colts  by    6  dog =       bears    Vegas:       colts  by  4.5
Zoltar:    dolphins  by    6  dog =      titans    Vegas:    dolphins  by  3.5
Zoltar:      eagles  by    0  dog =       lions    Vegas:      eagles  by    3
Zoltar:    steelers  by    6  dog =        jets    Vegas:    steelers  by  7.5
Zoltar:    patriots  by   12  dog =      browns    Vegas:    patriots  by   10
Zoltar:    redskins  by    0  dog =      ravens    Vegas:      ravens  by  3.5
Zoltar:     vikings  by    6  dog =      texans    Vegas:     vikings  by    6
Zoltar:     broncos  by    7  dog =     falcons    Vegas:     broncos  by    6
Zoltar:        rams  by    4  dog =       bills    Vegas:        rams  by    3
Zoltar:     raiders  by    7  dog =    chargers    Vegas:     raiders  by  4.5
Zoltar:     bengals  by    2  dog =     cowboys    Vegas:     bengals  by    1
Zoltar:     packers  by    6  dog =      giants    Vegas:     packers  by  7.5
Zoltar:    panthers  by   10  dog =  buccaneers    Vegas:    panthers  by    6

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week 5 Zoltar has only two suggestions:

1. Zoltar likes the Vegas underdog Redskins against the Ravens. Zoltar thinks the two teams are evenly matched and predicts the Ravens will not cover the 3.5 Vegas point spread.

2. Zoltar likes the Vegas favorite Panthers against the Buccaneers. Zoltar thinks the Panthers are 10 pojnts better than the Buccs and so the Panthers will cover the 6.0 Vegas point spread.

In week 4, Zoltar went a mediocre 3-2 against the Vegas point spread. For the year, Zoltar is 12-7 against the Vegas spread, for 63% accuracy. Historically, Zoltar is usually between 62% and 72% accuracy against the Vegas spread over the course of an entire season. Theoretically, if you must bet $110 to win $100 (typical) 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 and Cortana/Bing Predictions do when just trying to predict just which team will win a game. This isn’t useful except for parlay betting.

In week 4, just predicting winners, Zoltar was just 8-7. Bing was only 7-8.

For the season, just predicting winners, Zoltar is 36-27 (57% accuracy). Bing is 32-31 (51% accuracy).

Note: Zoltar sometimes predicts a 0-point margin of victory. In those situations, to pick a winner so I can compare against Bing, in the first four weeks of the season, Zoltar picks the home team to win. After week 4, Zoltar uses historical data for the current season.


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

2 Responses to NFL 2016 Week 5 Predictions – Zoltar Likes Redskins and Panthers

  1. Rob Potter says:

    Excellent picks. Your model is one of the best I’ve seen for picking winners against the spread. Do you happen to know the record of your picks if one were to bet all 14 games per week using the spreads your model predicts, instead of only betting when the line is a 3.0 difference?

    • Thanks Rob. I haven’t looked at Zoltar’s record so far this season when playing all predictions rather than just the ones where Zoltar and Vegas differ by more than 3.0 points. But in previous years, Zoltar usually does pretty well, but not quite as good as when using the 3.0 delta criterion. As I recall, last season, when betting on all games, Zoltar was 59% against the spread. Interestingly, I do remember that when I cranked the delta value up to 5.0, Zoltar’s results got worse because the system had fewer betting opportunities and randomness kicked in.


Comments are closed.