Data science and the business of Major League Baseball
Who is this presentation for?Business stakeholders, strategy and analytics Leadership, data scientists, data analysts, data engineers, business intelligence analysts, and business intelligence developers
When most people think of Major League Baseball (MLB) and data science, they think of Moneyball, Sabermetrics, or Statcast AI – data science from action on the field. However, with millions of local and global fans engaging with America’s Pastime every day, and with 30 “client” organizations (i.e., each MLB club), there is also a great deal of action happening off the field. From ticket and apparel purchases to live game streaming and app check-ins to email activity and clickstreams, MLB leverages data science to better serve its fans and clubs.
Matt Horton, Josh Hamilton, and Aaron Owen offer an overview of some of the many projects MLB’s Data Science team undertakes. Incorporating such tools as SAS, Python, and AWS Sagemaker, these projects include predicting ticket purchasers’ likelihoods to purchase again, evaluating prospective season schedules, estimating customer lifetime value, home-game promotion optimization, quantifying the strength of fan avidity, and monitoring the health of monthly subscribers of MLB’s game-streaming service.
Prerequisite knowledgeBasic understanding of statistics and data science concepts
What you'll learn
Major League Baseball
Aaron Owen is a data scientist at Major League Baseball, where he leverages his skills to solve business problems for the organization and its 30 teams. Aaron holds an MS and PhD in evolutionary biology and was previously a professor at both the City University of New York and New York University.
Major League Baseball
Matt Horton is the Senior Director of Data Science at Major League Baseball (MLB). In his 11+ years at MLB, Matt has developed numerous projects including predicting ticket buyers’ future purchasing behavior to aid teams in prioritizing their marketing efforts and building a framework for predicting and preventing subscriber churn for MLB’s game-streaming service, MLB.TV. Most recently, Matt’s team has been focused on quantifying fans’ relationships with their favorite teams, modeling trends in both team and league-wide attendance, and estimating fans’ future engagement with MLB.
Prior to joining MLB, Matt worked for Rosetta and Accenture. He has a BS in Statistics from the University of Tennessee and a Masters in Applied Statistics from Cornell University.
In addition to him being a huge baseball fan, Matt is also an avid fan of sports in general rooting for teams from his home state of Tennessee, including the Volunteers, Titans, Predators, and Grizzlies.
Josh Hamilton is a data scientist at Major League Baseball where he works with the league and its 30 teams building data pipelines and predictive models. Previously, Josh helped build data infrastructure and recommender systems for a movie streaming company and worked as a product manager for a platform as a service startup. He studied finance and economics and holds his MS in applied statistics from the University of Alabama.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of Strata Data Conference contacts