Great Lakes Analytics in Sports Conference
Assistant Professor, Business Information and Analytics |
University of Denver
Integer Programming and Daily Fantasy Sports --
A Winning Strategy?
Daily fantasy sports contests, or fantasy sports contests in general, are at their most basic level a problem of choosing a set of players that will hopefully outperform the set(s) of players chosen by your opponent(s). In this talk we will illustrate how to frame the selection problem as an integer programming optimization problem subject to a variety of constraints that are dependent upon the particular sport and/or strategy. Unfortunately, the optimization problem is reliant on an unknown objective function. However, we show how this unknown function might be predicted using a general linear regression model.
Ryan Elmore is an assistant professor in the Department of Business Information and Analytics, Daniels College of Business at the University of Denver. Prior to Daniels, he worked as a senior scientist in the Computational Sciences Center at the National Renewable Energy Lab in Golden, Colo. He has also held positions at the Australian National University, Colorado State University, and Slide, Inc. His work in sports statistics has led to the position of Associate Editor for the Journal of Quantitative Analysis of Sports (2015–present) and consultant to the Denver Nuggets professional basketball team.
Follow Ryan on Twitter
Listen to a podcast interview with Ryan and GLASC director Scott Tappa
Back to Great Lakes Analytics in Sports Conference