NFL 2016 Week 7 Predictions – Zoltar Predicts Many Close Games

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 7 of the 2016 NFL season:

Zoltar:     packers  by   10  dog =       bears    Vegas:     packers  by    9
Zoltar:      giants  by    1  dog =        rams    Vegas:      giants  by    3
Zoltar:     vikings  by    4  dog =      eagles    Vegas:     vikings  by  2.5
Zoltar:        jets  by    6  dog =      ravens    Vegas:      ravens  by    0
Zoltar:     bengals  by   12  dog =      browns    Vegas:     bengals  by   10
Zoltar:      chiefs  by    7  dog =      saints    Vegas:      chiefs  by    7
Zoltar:       colts  by    0  dog =      titans    Vegas:      titans  by    4
Zoltar:       bills  by    1  dog =    dolphins    Vegas:       bills  by    3
Zoltar:    redskins  by    0  dog =       lions    Vegas:       lions  by    1
Zoltar:     raiders  by    0  dog =     jaguars    Vegas:     jaguars  by  1.5
Zoltar:  buccaneers  by    0  dog = fortyniners    Vegas:  buccaneers  by    2
Zoltar:     falcons  by    9  dog =    chargers    Vegas:     falcons  by  6.5
Zoltar:    patriots  by    0  dog =    steelers    Vegas:    patriots  by  7.5
Zoltar:   cardinals  by    4  dog =    seahawks    Vegas:   cardinals  by  1.5
Zoltar:     broncos  by    6  dog =      texans    Vegas:     broncos  by    7

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. So for week 7 Zoltar has only three suggestions:

1. Zoltar likes the Jets against the Ravens. The Vegas line is “pick-em” but Zoltar thinks the Jets are six points better than the Ravens.

2. Zoltar likes the Vegas underdog Steelers against the Patriots. Zoltar thinks the two teams are evenly matched (and that the injury to the Steeler’s QB is not critical) and so the Patriots will not cover the 7.5 Vegas point spread (so a bet on the Steelers will pay off if the Steelers win outright, or if the Patriots win but by 7 points or less).

3. Zoltar likes the Vegas underdog Colts against the Titans. Vegas has the Titans favored by 4.0 points by Zoltar says the teams are evenly matched.

(Note: my original post had the wrong point spread for a few games, including Colts-Titans, because the program didn’t take into account the Giants-Rams game was in London).

In week 6, Zoltar went 2-1 against the Vegas point spread. For the year, Zoltar is 15-9 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 6, just predicting winners, Zoltar was a pretty good 10-5. Bing was decent at 8-7.

For the season, just predicting winners, Zoltar is 55-37 (60% accuracy). Bing is 48-44 (52% 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 (home field records) for the current season.


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

2 Responses to NFL 2016 Week 7 Predictions – Zoltar Predicts Many Close Games

  1. Rob Potter says:

    Another great week for Zoltar! I’m curious if Zoltar takes any intangibles into account such as weather, injuries, “must win” games or home field advantage? Also, does Zoltar also predict the game point total with accuracy over 50% or is he not built for that? I find predictive algorithms/models very fascinating and I’m curious about the capabilities of a well tuned model for sports handicapping.

Comments are closed.