I wrote a computer program called Zoltar that predicts the results of NFL football games. Unlike many prediction programs that use classical statistics techniques, Zoltar uses an information-theoretic approach.
Zoltar’s point spread predictions for week 14 of the 2015 NFL season are:
Zoltar favorite = cardinals by 7 underdog = vikings Zoltar favorite = panthers by 11 underdog = falcons Zoltar favorite = bears by 6 underdog = redskins Zoltar favorite = bengals by 6 underdog = steelers Zoltar favorite = fortyniners by 2 underdog = browns Zoltar favorite = colts by 5 underdog = jaguars Zoltar favorite = chiefs by 10 underdog = chargers Zoltar favorite = jets by 9 underdog = titans Zoltar favorite = eagles by 2 underdog = bills Zoltar favorite = lions by 0 underdog = rams Zoltar favorite = seahawks by 4 underdog = ravens Zoltar favorite = buccaneers by 6 underdog = saints Zoltar favorite = broncos by 17 underdog = raiders Zoltar favorite = packers by 7 underdog = cowboys Zoltar favorite = patriots by 3 underdog = texans Zoltar favorite = dolphins by 4 underdog = giants
Notice that in the Lions vs. Rams game Zoltar predicts a tie game. When this happens, just in order to calculate a head-to-head winning percentage, Zoltar predicts the team with the higher internal rating will win (according to Zoltar, Lions = 2004 and Rams = 1912).
Zoltar’s predictions are close to the Las Vegas point spreads, but there are 4 games where Zoltar sees a theoretical betting opportunity:
* Zoltar says the Panthers will beat the Falcons by 11 points but Vegas says the Panthers are favored by only 7.5 points so Zoltar recommends betting on the Vegas favorite Panthers. 1
* Zoltar says the Colts will beat the Jaguars 5 points but Vegas says the Jaguars will win by 1 point so Zoltar recommends betting on the Vegas underdog Colts. 0
* Zoltar says the Seahawks will beat the Ravens by only 4 points but Vegas says the Seahawks will win by 9 points so Zoltar recommends betting on the Vegas underdog Ravens.
* Zoltar says the Broncos will win by an enormous 17 points over the Raiders but Vegas says the Broncos will win only by 7.5 points so Zoltar recommends betting on the Vegas favorite Broncos.
For the season, through week 13, in head-to-head predictions, meaning just predicting the winner of a game (which isn’t particularly useful), Zoltar has gone 144-48 for 75% accuracy. Bing Predictions is 122-70 for 64% accuracy. By the way, if you simply picked the home team to win, you’d go a poor 102-90 = 53% accuracy. If you simply pick the Las Vegas favorite, you’d go a pretty decent 117-69 = 63%.
Update Tuesday, Dec. 15, 2015: It wasn’t a good week for Zoltar. In picking just the winner, Zoltar was a horrible 8-8, the system’s worst week this season by far. Bing predictions was better at 9-7, the first week this season where Bing has done better than Zoltar. Against the Vegas point spread, Zoltar was a disastrous 1-4, only correctly predicting the Panthers to cover the 7.5 spread against the Falcons game. Ugh. First week this season where Zoltar was under .500 against the spread.