NFL 2016 Week 8 Predictions – Zoltar Recommends the Bills and the Broncos

Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 8 of the 2016 NFL season:

Zoltar:      titans  by    2  dog =     jaguars    Vegas:      titans  by  3.5
Zoltar:     bengals  by    5  dog =    redskins    Vegas:     bengals  by    3
Zoltar:    patriots  by    2  dog =       bills    Vegas:    patriots  by    6
Zoltar:    seahawks  by    3  dog =      saints    Vegas:    seahawks  by    3
Zoltar:     raiders  by    0  dog =  buccaneers    Vegas:  buccaneers  by    1
Zoltar:        jets  by    5  dog =      browns    Vegas:        jets  by    3
Zoltar:   cardinals  by    0  dog =    panthers    Vegas:    panthers  by    3
Zoltar:      texans  by    6  dog =       lions    Vegas:      texans  by    3
Zoltar:      chiefs  by    1  dog =       colts    Vegas:      chiefs  by  2.5
Zoltar:     broncos  by   11  dog =    chargers    Vegas:     broncos  by    6
Zoltar:     packers  by    0  dog =     falcons    Vegas:     falcons  by    3
Zoltar:     cowboys  by    2  dog =      eagles    Vegas:     cowboys  by  4.5
Zoltar:     vikings  by    7  dog =       bears    Vegas:     vikings  by  5.5

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 only two suggestions:

1. Zoltar likes the Vegas underdog Bills against the Patriots. Zoltar thinks the Patriots are 2.0 points better than the Bills but Vegas says the Patriots will win by 6.0 points. (But note: Every single time this season Zoltar has recommended against the Patriots, Zoltar has been wrong).

2. Zoltar likes the Vegas favorite Broncos against the Chargers. Zoltar thinks the Broncos are 11.0 points better than the Chargers but Vegas says the Broncos will win only by 5.0 points.

In week 7, Zoltar went 2-1 against the Vegas point spread. For the year, Zoltar is 17-10 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 7, just predicting winners, Zoltar was a pretty good 10-4. Bing was OK at 7-7. I didn’t count the Cardinals-Seahawks game, which ended in a tie.

(Note on 10/26/2016 — I just looked at the Cortana Predictions Web site and they counted the Cardinals-Seahawks game as an incorrect prediction; I think they’re too hard on themselves so I’ll continue to ignore that game for both Cortana and Zoltar).

For the season, just predicting winners, Zoltar is 65-41 (61% accuracy). Bing is 55-51 (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. Week 7 was very unusual in that Zoltar had five of these 0-point margins; usually the home team will be picked but in week 7, most of the visiting teams were picked. (For example, going into week 7, the Raiders had a 3-0 record when visitors, so they were picked just to win over the home team Jaguars who had a 1-2 home record).


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