Predicting the results of NFL football games is a fascinating problem. I wrote a computer program called Zoltar to do just that. Unlike many prediction programs that use classical statistics techniques, Zoltar uses an information-theoretic approach.

Zoltar’s point spread predictions for the first round of the playoffs (week 18) of the 2015 NFL season are:

Zoltar favorite =      chiefs  by    0  underdog =      texans
Zoltar favorite =     bengals  by    5  underdog =    steelers
Zoltar favorite =    seahawks  by    0  underdog =     vikings
Zoltar favorite =     packers  by    0  underdog =    redskins

Here is are the Vegas point spreads:

Vegas favorite :    chiefs    by    3
Vegas favorite :    steelers  by  2.5
Vegas favorite :    seahawks  by  5.5
Vegas favorite :    redskins  by    1

So, Zoltar says three of the four playoff games are evenly matched, which really isn’t a surprise. The two games where Zoltar would make a betting recommendation are the Steelers vs. Bengals and the Seahawks vs. Vikings game.

Zoltar thinks the Bengals will win by 5 points but Vegas says the Steelers will win by 2.5 (i.e. 3 or more), so Zoltar would recommend betting on the Vegas underdog Bengals. You’d win your bet if the Bengals win outright or if the Steelers win by 2 points or less.

Because Zoltar says the Seahawks and Vikings are evenly matched, but Vegas says the Seahawks will win by 5.5 (i.e., 6) or more points, Zoltar would recommend betting on the Vegas underdog Vikings. You’d win your bet if the Vikings win outright or if the Seahawks win but by 5 points or fewer.

For the 2015 season, through week 17 (last regular season games), in head-to-head predictions, meaning just predicting the winner of a game (which isn’t particularly useful except for parlay betting), Zoltar has gone 185-71 for 72% accuracy. Bing Predictions is 161-95 for 63% accuracy.

For the regular season, if you simply picked the home team to win, you’d have gone 138 correct and 118 wrong for 54% accuracy.

But if you just picked the Las Vegas point spread favorite to win each game, you’d have gone 153 correct and 91 wrong for 63% accuracy.

Update on Monday, 01/11/2015:

For last week’s predictions, Zoltar was correct in three out of four games when predicting just the winner — Zoltar correctly predicted the Chiefs, Seahawks, and Packers would win but incorrectly predicted the Bengals would beat the Steelers.

Against the Vegas point spread, Zoltar was a perfect 2-0, correctly advising bets on Vegas underdogs Vikings and Bengals, believing that the favorites (Seahawks and Steelers respectively) wouldn’t cover the point spread. The Seahawk won by only 1 point and the Steelers won by only 2 points.