Machine Learning and Hockey: Predicting Average NHL Home Game Attendance

Julie Vaughan Butler University
Faculty Sponsor(s): Barry King Butler University, Jennifer Rice
This research works to identify predictor variables for National Hockey League average attendance. The seasons examined are the 2013 hockey season through the beginning of the 2017 hockey season. Multiple linear regression and three machine learning algorithms – random forest, M5 prime, and extreme gradient boosting – are employed to predict out-of-sample average home game attendance. Extreme gradient boosting generated the lowest out-of-sample root mean square error. The team identifier (team name), the number of Twitter followers (a surrogate for team popularity), median ticket price, and arena capacity have appeared as the top four predictor variables.
Business & Economics
Oral Presentation

When & Where

11:00 AM
Jordan Hall 174