Presented By
O’Reilly + Cloudera
Make Data Work
March 25-28, 2019
San Francisco, CA

Sports analytics in the wild using player-tracking data

Patrick Lucey (Stats Perform)
10:00am–10:30am Tuesday, March 26, 2019
Location: 2022
Average rating: *****
(5.00, 4 ratings)

Imagine watching a sports game and having the ability to immediately find all plays that are similar to what just happened. Better still, imagine having the ability to draw a play with X’s and O’s on an interface (like a coach draws on a chalkboard) and find similar plays instantaneously—and conduct analytics on those plays (when those plays occur, how many points a team expects from that play, etc.). Or what about having the ability to evaluate the performance of a player or a team in a given situation and compare it against another player in exactly the same position. This approach is called interactive sports analytics.

Patrick Lucey describes methods to find play similarity using multiagent trajectory data and predict fine-grained plays, using examples using STATS SportVU data in basketball and soccer. Patrick then discusses how to go beyond center-of-mass tracking (i.e., dots) and capture body-pose information from broadcast video to take analysis to the next level.

Photo of Patrick Lucey

Patrick Lucey

Stats Perform

Patrick Lucey is the chief scientist of artificial intelligence at Stats Perform, where his goal is to maximize the value of the 35+ years worth of sports data. His main research interests are in artificial intelligence and interactive machine learning in sporting domains. Previously, Patrick spent five years at Disney Research, where he conducted research into automatic sports broadcasting using large amounts of spatiotemporal tracking data, and was a postdoctoral researcher at the Robotics Institute at Carnegie Mellon University and the Department of Psychology at the University of Pittsburgh, conducting research on automatic facial expression recognition. He holds a BEng (EE) from the University of Southern Queensland and a PhD from QUT, Australia. He was a coauthor of the best paper at the 2016 MIT Sloan Sports Analytics Conference and in 2017 and 2018 was coauthor of best paper runner-up at the same conference. Patrick has also won best paper awards at the INTERSPEECH (2007) and the Winter Conference on Applications of Computer Vision (WACV) (2014) international conferences.