NFL 2016 Week 10 Predictions – Zoltar likes Buccaneers, Jets, Dolphins

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 10 of the 2016 NFL season:

Zoltar:      ravens  by   10  dog =      browns    Vegas:      ravens  by   10
Zoltar:  buccaneers  by    6  dog =       bears    Vegas:       bears  by    1
Zoltar:     falcons  by    0  dog =      eagles    Vegas:      eagles  by    1
Zoltar:        jets  by    6  dog =        rams    Vegas:        jets  by    2
Zoltar:     packers  by    3  dog =      titans    Vegas:     packers  by  2.5
Zoltar:     broncos  by    1  dog =      saints    Vegas:      saints  by  1.5
Zoltar:    panthers  by    1  dog =      chiefs    Vegas:    panthers  by    3
Zoltar:      texans  by    4  dog =     jaguars    Vegas:      texans  by  1.5
Zoltar:     vikings  by    0  dog =    redskins    Vegas:    redskins  by  2.5
Zoltar:    dolphins  by    0  dog =    chargers    Vegas:    chargers  by  3.5
Zoltar:    steelers  by    4  dog =     cowboys    Vegas:    steelers  by  2.5
Zoltar:   cardinals  by   11  dog = fortyniners    Vegas:   cardinals  by 13.5
Zoltar:    patriots  by    6  dog =    seahawks    Vegas:    patriots  by  7.5
Zoltar:     bengals  by    0  dog =      giants    Vegas:      giants  by  2.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. So for week 10 Zoltar has three suggestions:

1. Zoltar likes the Vegas underdog Buccaneers against the Bears. Zoltar thinks the Buccaneers are 6 points better than the Bears, but Vegas has the Bears as 1.0 point favorites. This 7-point delta is enormous and I’m suspicious I’ve got some bad data. Will check later this week.

2. Zoltar likes the Vegas favorite Jets against the Rams. Zoltar thinks the Jets will win by 6 points but Vegas says the Jets will win by only 2.0 points.

3. Zoltar (barely) likes the Vegas underdog Dolphins against the Chargers. Zoltar thinks the two teams are exactly evenly matched but Vegas has the Chargers to win by 3.5 points.


In week 9, Zoltar went 0-1 against the Vegas point spread. Note: my original predictions for week 9 had incorrect point spread data, which if used would have made Zoltar a hideous 0-3 for the week.

For the year, Zoltar is 18-12 against the Vegas spread, for exactly 60% 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 against the spread.

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 9, just predicting winners, Zoltar was a good 10-3. Bing was very good too at 10-3. Zoltar’s and Cortana’s predictions were similar except Zoltar got the Broncos-Raiders game correct (Cortana was wrong) and Cortana got the Steelers-Ravens game correct (Zoltar was wrong).

For the season, just predicting winners, Zoltar is 85-46 (65% correct) and Cortana/Bing is 73-58 (56% correct). Neither record includes two tie games this season.


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