Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 15 of the 2016 NFL season:

Zoltar:    seahawks  by   10  dog =        rams    Vegas:    seahawks  by   14
Zoltar:    dolphins  by    0  dog =        jets    Vegas:    dolphins  by  2.5
Zoltar:    steelers  by    0  dog =     bengals    Vegas:    steelers  by  3.5
Zoltar:      chiefs  by   11  dog =      titans    Vegas:      chiefs  by  5.5
Zoltar:       bills  by   15  dog =      browns    Vegas:       bills  by   10
Zoltar:     packers  by    4  dog =       bears    Vegas:     packers  by  6.5
Zoltar:     vikings  by    6  dog =       colts    Vegas:     vikings  by    4
Zoltar:      texans  by   11  dog =     jaguars    Vegas:      texans  by  5.5
Zoltar:      giants  by    1  dog =       lions    Vegas:      giants  by  4.5
Zoltar:      ravens  by    6  dog =      eagles    Vegas:      ravens  by    6
Zoltar:     falcons  by   15  dog = fortyniners    Vegas:     falcons  by 13.5
Zoltar:   cardinals  by    6  dog =      saints    Vegas:   cardinals  by  2.5
Zoltar:     raiders  by    4  dog =    chargers    Vegas:     raiders  by    3
Zoltar:    patriots  by    0  dog =     broncos    Vegas:    patriots  by    3
Zoltar:     cowboys  by    6  dog =  buccaneers    Vegas:     cowboys  by    7
Zoltar:    redskins  by    1  dog =    panthers    Vegas:    redskins  by  4.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week 15 Zoltar has 8 suggestions.

1. Zoltar likes the Vegas underdog Rams against the Seahawks. Zoltar thinks the Seahawks are 10.0 points better than the Rams but Vegas says the Seahawks will win by 14.0 points.

2. Zoltar likes the Vegas underdog Bengals against the Steelers. Zoltar thinks the two teams are evenly matched but Vegas says the Steelers will win by 3.5 points.

3. Zoltar likes the Vegas favorite Chiefs against the Titans. Zoltar thinks the Chiefs will win by 11.0 points but Vegas says the Chiefs will win by only 5.5 points.

4. Zoltar likes the Vegas favorite Bills against the Browns. Zoltar thinks the Bills will win by 15.0 points but Vegas says the Bills will win by “only” 10.0 points.

5. Zoltar likes the Vegas favorite Texans against the Jaguars. Zoltar thinks the Texans will win by 11.0 points but Vegas says the Texans will win by only 5.5 points.

6. Zoltar likes the Vegas underdog Lions against the Giants. Zoltar thinks the Giants are just 1.0 point better than the Lions but Vegas says the Giants will win by 4.5 points.

7. Zoltar likes the Vegas favorite Cardinals against the Saints. Zoltar thinks the Cardinals are 6.0 points better than the Saints but Vegas says the Cardinals will win by only 2.5 points.

8. Zoltar likes the Vegas underdog Panthers against the Redskins. Zoltar thinks the Redskins are just 1.0 point better than the Panthers but Vegas says the Redskins will win by 4.5 points.

In week 14, Zoltar went a good 5-2 against the Vegas point spread.

For the season so far, Zoltar is 34-20 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 14, just predicting winners, Zoltar was a so-so 11-5. Cortana/Bing was a very good 13-3 for the week.

For the season, just predicting winners, Zoltar is 140-66 (68% accuracy). Cortana/Bing is 128-78 (62% 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).

In week 15, this strategy didn’t work too well. There were five games where Zoltar thought the two teams were even. Of these five, the team with the better home-vs-away record won only twice.

1969 “Computer Football Game” from Electronic Data Controls Co.
See https://boardgamegeek.com/boardgame/14190/computer-sports-games-football-baseball-basketball