Great Lakes Analytics in Sports Conference
Associate Professor, Mathematical Biology | University of Wisconsin-La Crosse
Data Scientist | Pro Football Focus
Using Machine Learning to Classify Quality and
Style of Play at the Quarterback Position
When it comes to winning football games, success at the quarterback position is the most highly correlated and predictive variable. As such, finding, evaluating, and sustaining a high-level passing attack is one of the most important tasks in all of pro sports. Using Pro Football Focus data, we determine aspects of a quarterback’s throw profile that are the most stable season to season, as well as those that are most predictive of future performance. With a variety of machine learning techniques at our disposal, we use these insights to classify quarterback play, and these groups provide substantial information for both explanatory and predictive purposes for teams moving forward.
Eric Eager received his Ph.D. in mathematical biology in 2012, and has been a professor at the University of Wisconsin – La Crosse since. He is the author of over 20 papers in applied mathematics and the scholarship of teaching and learning. He joined Pro Football Focus in 2015, and has been one of their analytics leads since January 2017.
Follow Eric on Twitter
Listen to a podcast interview with Eric and GLASC director Scott Tappa
Watch a video of Eric's 2018 GLASC presentation
Back to Great Lakes Analytics in Sports Conference