NFL 2016 Week 17 Predictions – Zoltar Has Many Suggestions

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 17 (the last regular week) of the 2016 NFL season:


Zoltar:    panthers  by    0  dog =  buccaneers    Vegas:  buccaneers  by  6.5
Zoltar:       bills  by    0  dog =        jets    Vegas:       bills  by  3.5
Zoltar:     bengals  by    5  dog =      ravens    Vegas:     bengals  by  2.5
Zoltar:       colts  by   10  dog =     jaguars    Vegas:       colts  by  4.5
Zoltar:      texans  by    0  dog =      titans    Vegas:      titans  by    3
Zoltar:    patriots  by    4  dog =    dolphins    Vegas:    patriots  by  9.5
Zoltar:     cowboys  by    4  dog =      eagles    Vegas:      eagles  by    4
Zoltar:     vikings  by   10  dog =       bears    Vegas:     vikings  by  5.5
Zoltar:    steelers  by   18  dog =      browns    Vegas:    steelers  by  6.5
Zoltar:     falcons  by    6  dog =      saints    Vegas:     falcons  by    7
Zoltar:      chiefs  by    9  dog =    chargers    Vegas:      chiefs  by  5.5
Zoltar:    redskins  by    4  dog =      giants    Vegas:    redskins  by    8
Zoltar:   cardinals  by    4  dog =        rams    Vegas:   cardinals  by    6
Zoltar:     raiders  by    0  dog =     broncos    Vegas:     broncos  by    1
Zoltar:    seahawks  by   11  dog = fortyniners    Vegas:    seahawks  by  9.5
Zoltar:     packers  by    0  dog =       lions    Vegas:     packers  by  3.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week 17 Zoltar has 10 suggestions — the most suggestions for any one week in Zoltar’s history. This is due to a lot of key injuries, and teams who are already qualified for the playoffs (or already eliminated) and so will rest important players.

1. Zoltar likes the Vegas underdog Panthers against the Buccaneers. Zoltar thinks the two teams are evenly matched but Vegas says the Buccaneers will win by 6.5 points.

2. Zoltar likes the Vegas underdog Jets against the Bills. Again, Zoltar thinks the two teams are evenly matched but Vegas says the Bills will win by 3.5 points.

3. Zoltar likes the Vegas favorite Colts over the Jaguars. Zoltar thinks the Colts are 10.0 points better than the Jaguars but Vegas says the Colts will win by only 4.5 points.

4. Zoltar (somewhat inexplicably) likes the Vegas underdog Dolphins against the Patriots. Zoltar thinks the Patriots are only 4.0 points better than the Dolphins but Vegas says the Patriots will win by 9.5 points.

5. Zoltar likes the Vegas underdog Cowboys against the Eagles. Zoltar thinks the Cowboys are 4.0 points better than the Eagles, but Vegas says the Eagles will win by 4.0 points.

6. Zoltar likes the Vegas favorite Vikings over the Bears. Zoltar thinks the Vikings are 10.0 points better than the Bears but Vegas says the Vikings will win by only 5.5 points.

7. Zoltar likes the Vegas favorite Steelers over the Browns. Zoltar thinks the Steelers are an enormous 18.0 points better than the Browns but Vegas says the Steelers will win by only 6.5 points.

8. Zoltar likes the Vegas favorite Chiefs over the Chargers. Zoltar thinks the Chiefs are 9.0 points better than the Chargers but Vegas says the Chiefs will win by only 5.5 points.

9. Zoltar likes the Vegas underdog Giants against the Redskins. Zoltar thinks the Redskins are only 4.0 points better than the Giants, but Vegas says the Redskins will win by 8.0 points.

10. Zoltar likes the Vegas underdog Lions against the Packers. Zoltar thinks the two teams are evenly matched, but Vegas says the Packers will win by 3.5 points.


In week 16, Zoltar went 0-0 against the Vegas point spread. Zoltar had one preliminary suggestion for the Rams-49ers game but a mid-week change in the point spread erased that suggestion.

For the season so far, Zoltar is 37-25 against the Vegas spread, for 60% 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 16, just predicting winners, Zoltar was a mediocre 9-7. Cortana/Bing was also 9-7 just predicting winners.

For the season, just predicting winners, Zoltar is 161-77 (68% accuracy). Cortana/Bing is 149-89 (63% accuracy). There have been two ties this season, which I don’t include.

Note: Zoltar sometimes predicts a 0-point margin of victory. In those situations, to pick a winner so I can compare against Cortana/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 (which usually ends up in a prediction that the home team will win).

zoltarweek17predictionsrun

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