NFL 2016 Week 9 Predictions – Zoltar Likes Three Vegas Underdogs

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 9 of the 2016 NFL season:

Zoltar:     falcons  by    0  dog =  buccaneers    Vegas:     falcons  by  3.5
Zoltar:     cowboys  by    6  dog =      browns    Vegas:     cowboys  by  7.5
Zoltar:     vikings  by    8  dog =       lions    Vegas:     vikings  by  6.5
Zoltar:      chiefs  by   11  dog =     jaguars    Vegas:      chiefs  by    9
Zoltar:      giants  by    1  dog =      eagles    Vegas:      giants  by  2.5
Zoltar:        jets  by    0  dog =    dolphins    Vegas:    dolphins  by  3.5
Zoltar:    steelers  by    3  dog =      ravens    Vegas:      ravens  by  2.5
Zoltar:      saints  by    0  dog = fortyniners    Vegas:      saints  by    3
Zoltar:    panthers  by    2  dog =        rams    Vegas:    panthers  by    3
Zoltar:     packers  by    6  dog =       colts    Vegas:     packers  by    7
Zoltar:    chargers  by    4  dog =      titans    Vegas:    chargers  by    5
Zoltar:     broncos  by    0  dog =     raiders    Vegas:     raiders  by    1
Zoltar:    seahawks  by    6  dog =       bills    Vegas:    seahawks  by    7

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. So for week 8 Zoltar has three suggestions (actually just two suggestions — see note below):

1. Zoltar likes the Vegas underdog Buccaneers against the Falcons. Zoltar thinks the two teams are exactly evenly matched but Vegas says the Falcons will win by 3.5 points. (A bet on the Buccaneers will pay off if the Buccaneers win outright or if the Falcons win but by 3 points or less).

2. Zoltar likes the Vegas underdog Jets against the Dolphins. Zoltar thinks the two teams are exactly evenly matched but Vegas says the Dolphins will win by 4.0 points — so a bet on the Jets will pay off if the Jets win or if the Dolphins win but by less than 4 points.

3. Zoltar likes the Vegas underdog Steelers against the Ravens. Zoltar thinks the Steelers are 3 points better than the Ravens but Vegas says the Ravens are 2.5 points better than the Steelers — it’s quite unusual for Zoltar and Vegas to differ so much, making me suspect there is perhaps an injury issue for the game that Zoltar/me is not aware of.

Note: I double checked the Vegas point spread for the Steelers-Ravens and the Jets-Dolphins games, and my data was wrong. The Steelers are favored by 3.0 points, so Zoltar does not suggest betting on this game. I’m not sure how my point spread data file got messed up. I also had the wrong point spread for the Jets-Dolphins game — Dolphins are favored by 4.0 points not 3.5 points.


In week 8, Zoltar went 1-1 against the Vegas point spread. For the year, Zoltar is 18-11 against the Vegas spread, for 62% accuracy. Historically, Zoltar is usually between 62% and 72% accuracy against the Vegas spread over the course of an entire season, so this is a relatively poor season for Zoltar.

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 8, just predicting winners, Zoltar was a very good 10-2. Bing was very good too at 8-4. I didn’t count the Redskins-Bengals game, which ended in a 27-27 tie. This was the second tie game this season — Zoltar hates ties.

For the season, just predicting winners, Zoltar is 74-43 for 64% correct. Cortana/Bing is 63-55 for 53% correct. (Neither record includes the two tie games this season).


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