NFL 2017 Week 1 Predictions – Zoltar Likes Three Favorites and Two Underdogs

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 1 of the 2017 NFL season:

Zoltar:    patriots  by    6  dog =      chiefs    Vegas:    patriots  by    9
Zoltar:       bills  by    6  dog =        jets    Vegas:       bills  by    7
Zoltar:     falcons  by    5  dog =       bears    Vegas:     falcons  by    7
Zoltar:      ravens  by    0  dog =     bengals    Vegas:     bengals  by    3
Zoltar:    steelers  by    6  dog =      browns    Vegas:    steelers  by    9
Zoltar:       lions  by    6  dog =   cardinals    Vegas:       lions  by    1
Zoltar:      texans  by    9  dog =     jaguars    Vegas:      texans  by  4.5
Zoltar:    dolphins  by    5  dog =  buccaneers    Vegas:  buccaneers  by    2
Zoltar:     raiders  by    0  dog =      titans    Vegas:      titans  by    1
Zoltar:    redskins  by    6  dog =      eagles    Vegas:    redskins  by    1
Zoltar:       colts  by    0  dog =        rams    Vegas:       colts  by    3
Zoltar:     packers  by    2  dog =    seahawks    Vegas:     packers  by    3
Zoltar:    panthers  by    0  dog = fortyniners    Vegas:    panthers  by    6
Zoltar:     cowboys  by    6  dog =      giants    Vegas:     cowboys  by  3.5
Zoltar:     vikings  by    5  dog =      saints    Vegas:     vikings  by  3.5
Zoltar:     broncos  by    6  dog =    chargers    Vegas:     broncos  by  3.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week 1 Zoltar has five suggestions. However, week #1 is a lot of guesswork, for both Zoltar and Las Vegas. I rarely bet for real, and almost never in the first three weeks.

1. Zoltar likes the Vegas favorite Lions against the Cardinals. Zoltar thinks the Lions are 6 points better than the Cardinals but Vegas says the Lions will win only by 1.0 points.

2. Zoltar likes the Vegas favorite Texans against the Jaguars. Zoltar believes the Texans will win by a whopping 9 points but Vegas thinks the Texans will win by only 4.5 points, so Zoltar thinks the Texans will cover the spread.

3. Zoltar likes the Vegas underdog Dolphins over the Buccaneers. Zoltar thinks the Dolphins are 5 points better than the Buccaneers, but Vegas says the Buccaneers will win by 2, so Zoltar believes that not only will the Buccaneers not cover the spread, they won’t even win.

4. Zoltar likes the Vegas favorite Redskins against the Eagles. Zoltar thinks the Redskins are 6 points better than the Eagles but Vegas says the Redskins will win only by 1.0 points.

5. Zoltar likes the Vegas underdog San Francisco 49ers against the Carolina Panthers. Zoltar believes the two teams are evenly matched, but Vegas has the Panthers as 6-point favorites, so Zoltar thinks the Panthers may win, but they won’t cover the spread.

Theoretically, if you must bet $110 to win $100 (typical in Vegas) 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 does when just trying to predict just which team will win a game. This isn’t useful except for parlay betting.

Zoltar sometimes predicts a 0-point margin of victory (three of the games in week #1). 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 visiting team to win. After week 4, Zoltar uses historical data for the current season (which usually ends up in a prediction that the visiting team will win).

Zoltar fortune teller machine – Zoltar is a cool dude

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

2 Responses to NFL 2017 Week 1 Predictions – Zoltar Likes Three Favorites and Two Underdogs

  1. Rob Potter says:

    Here’s to another great season with magnificent Zoltar! I do have a question if you don’t mind:

    Is there a particular reason that you only suggest betting when there’s a greater than 3 point discrepancy? If I were to lower the threshold to +2 points to allow for more betting opportunities, or better yet adjust the bet unit size depending on the Zoltar-Vegas disparity, would a betting system be more profitable despite having a lower overall win percentage?

    Thank you for making Zoltar’s picks public and also for Bing Maps V8. Incredibly useful!

    • The 3-point threshold was determined by trail and error. As you point out, a lower threshold leads to more betting opportunities, but that is offset by a lower winning percentage.

Comments are closed.