Courtvision: Emerging from the Defensive Analytics Dark Ages

• Activity Number: 144
• Type: Invited
• Date/Time: Monday, August 4, 2014 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Sports
• Author(s): Kirk Goldsberry*+
• Companies: Harvard

Abstract

Although new forms of "player tracking" data have been around for years, to this point the potential of their impact remains unmet in terms of analytical contributions. In this talk, I will explore the state of analysis of player tracking data in the NBA, and identify future challenges in this exciting domain. In the past, player tracking data have been mined primarily for basic insights, such as understanding the spatial distribution of a player's shooting tendencies, or to extract very simple summary statistics, such as the distance traveled by a player in a given game. In this talk, I will present how the XY Hoops research group at Harvard is using advanced statistics and machine learning tools to demonstrate that more advanced analyses of these data are not only possible, but can provide valuable insights as well. Examples include "How should teams configure their defensive matchups to minimize a player's effectiveness?", "Who are the best decision makers in the NBA?", and "Who was responsible for the most points against in the NBA last season?"