We use team statistics to create models that predict outcomes of NFL games. Our models generate win probabilities and point spreads, and we consider six different models, each of which generates a unique prediction for a given game. Each model considers metrics from a number of different areas, such as turnovers, first downs, points scored, pace of play, offensive and defensive efficiency, time of possession, drive statistics, point differential, as well as a few metrics that we have created ourselves. Beyond these statistics, the models also consider factors such as “did a team make the playoffs last year?” and “how far is the away team traveling?” The article below focuses on the four Wild Card matchups for this coming weekend, but a breakdown of predictions for the entire 2016 NFL Playoffs can be found here.
Continue reading 2016 NFL Wild Card Predictions
All posts by Sam Walczak
2016 NFL Playoff Predictions
We use team statistics from the regular season to predict win probabilities and point spreads for NFL playoff games. We have a number of different models that are used to predict each game, and we build off of the first round matchups to create predictions all the way through the super bowl. Below are our predictions for this year’s playoffs.
Continue reading 2016 NFL Playoff Predictions
March Madness 2016 Recap
The 2016 tournament had good spots and bad – most notably Michigan State, whom my models ranked as the 1st/2nd best team in the field, but lost in their first game. Thankfully, there were some bright spots as well, led by Villanova, who was picked to win it all in only 2.5% of brackets submitted to ESPN, but my models had right up there with Michigan State as the 1st/2nd best team in the field. The sections below go into detail on some of the bigger hits and misses from the tournament as a whole, as well as the results for a few individual models.
Continue reading March Madness 2016 Recap