Data science and the business of Major League Baseball
Using SAS, Python, and AWS SageMaker, Major League Baseball's (MLB's) data science team outlines how it predicts ticket purchasers likelihood to purchase again, evaluates prospective season schedules, estimates customer lifetime value, optimizes promotion schedules, quantifies the strength of fan avidity, and monitors the health of monthly subscriptions to its game-streaming service.
|Talk Title||Data science and the business of Major League Baseball|
|Speakers||Aaron Owen (Major League Baseball), Matthew Horton (Major League Baseball), Josh Hamilton (Major League Baseball)|
|Conference||Strata Data Conference|
|Conf Tag||Make Data Work|
|Location||New York, New York|
|Date||September 24-26, 2019|
When most people think of 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’s 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 that MLB’s data science team undertakes. Incorporating tools such as SAS, Python, and AWS SageMaker, these projects include predicting ticket purchasers’ likelihood 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.