Zoltar is my NFL prediction computer program. Here are Zoltar’s predictions for week 12 of the 2016 NFL season:

Zoltar:     vikings  by    0  dog =       lions    Vegas:       lions  by  2.5
Zoltar:     cowboys  by    4  dog =    redskins    Vegas:     cowboys  by    7
Zoltar:       colts  by    2  dog =    steelers    Vegas:    steelers  by    6
Zoltar:    dolphins  by   10  dog = fortyniners    Vegas:    dolphins  by  7.5
Zoltar:      texans  by    8  dog =    chargers    Vegas:    chargers  by    0
Zoltar:       bills  by   10  dog =     jaguars    Vegas:       bills  by    7
Zoltar:      giants  by   10  dog =      browns    Vegas:      giants  by    7
Zoltar:      saints  by    4  dog =        rams    Vegas:      saints  by    7
Zoltar:     bengals  by    0  dog =      ravens    Vegas:      ravens  by  4.5
Zoltar:       bears  by    1  dog =      titans    Vegas:      titans  by  3.5
Zoltar:     falcons  by    1  dog =   cardinals    Vegas:     falcons  by  4.5
Zoltar:    seahawks  by    3  dog =  buccaneers    Vegas:    seahawks  by  5.5
Zoltar:    patriots  by    4  dog =        jets    Vegas:    patriots  by    8
Zoltar:     raiders  by    1  dog =    panthers    Vegas:     raiders  by    4
Zoltar:     broncos  by    4  dog =      chiefs    Vegas:     broncos  by  3.5
Zoltar:      eagles  by    4  dog =     packers    Vegas:      eagles  by  3.5

Zoltar theoretically suggests betting when the Vegas line is more than 3.0 points different from Zoltar’s prediction. For week 12 Zoltar has five suggestions:

1. Zoltar likes the Vegas underdog Colts against the Steelers. Zoltar thinks the Colts are 2.0 points better than the Steelers but Vegas says the Steelers are 6.0 points better than the Colts. (This 8.0-point difference between Zoltar and Vegas is huge and I need to check my data files to make sure I don’t have bad data).

2. Zoltar likes the Texans against the Chargers. Zoltar thinks the Texans are a big 8.0 points better than the Chargers but Vegas says the game is a “pick-em” (evenly matched). Again, the 8.0-point difference is really large.

3. Zoltar likes the Vegas underdog Bengals against the Ravens. Zoltar thinks the two teams are exactly evenly matched but Vegas has the Ravens as 4.5-point favorites.

4. Zoltar (barely) likes the Vegas underdog Bears against the Titans. Zoltar thinks the Bears are 1.0 point better than the Titans but Vegas says the Titans will win by 3.5 points.

5. Zoltar likes the Vegas underdog Jets against the Patriots. Zoltar thinks the Patriots are 4.0 points better than the Jets but Vegas says the Patriots are 8.0 points better. Note: Over the past two seasons, Zoltar has been 100% wrong when recommending against the Patriots.

In week 11, Zoltar went a mediocre 1-1 against the Vegas point spread, correctly suggesting the Redskins (who easily beat the Packers) but incorrectly suggesting the Texans (who lost to the Raiders).

For the season so far, Zoltar is 21-14 against the Vegas spread, for 60% 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 11, just predicting winners, Zoltar was a very good 11-3. Cortana/Bing had the same predictions as Zoltar and so was also 11-3 for the week.

For the season, just predicting winners, Zoltar is 104-55 (65% accuracy). Cortana/Bing is 91-68 (57% accuracy). There have been two ties, 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).