I attended a really interesting event at Localytics called: “Advances in Basketball Analytics Using Player Tracking Data”. The event was extremely insightful and shows how far we have gotten in predicting outcomes in sports such as basketball.
The speaker Alexander D'Amour is the acting Neyman Visiting Assistant Professor in the Department of Statistics at UC Berkeley. He is completing his PhD in Statistics at Harvard University, where he was a member of the Harvard Laboratory for Applied Statistical Methodology & Data Science, lead by Edoardo Airoldi.
In the 2013-2014 season, the National Basketball Association, in conjunction with STATS LLC, implemented a league-wide program to collect player-tracking data for all NBA games. The data feed now provides 24-FPS records of all players’ XY coordinates on the court, as well as XYZ coordinates for the ball. This data source has opened up new lines of inquiry into the quantitative analysis of basketball that have previously been hamstrung by a reliance on spatially naive box-score and play-by-play statistics. In the talk Alexander discussed several projects undertaken by himself and the XY Research group that use newly-available spatial data to work toward answering fundamental questions about basketball. Topics covered included expected possession value (a.k.a, EPV, or a stock-ticker for a possession), defensive shot charts, the impact of ball movement, and play detection.
