Title: Possession Sketches: Mapping NBA Strategies
We present Possession Sketches, a new machine learning method for organizing and exploring a database of basketball player-tracks. Our method organizes basketball possessions by offensive structure. We first develop a model for populating a dictionary of short, repeated, and spatially registered actions. Each action corresponds to an interpretable type of player movement. We examine statistical patterns in these actions, and show how they can be used to describe individual player behavior. Leveraging this vocabulary of actions, we develop a hierarchical model that describes interactions between players. Our approach draws on the topic-modeling literature, extending Latent Dirichlet Allocation (LDA) through a novel representation of player movement data which uses techniques common in animation and video game design. We show that our model is able to group together possessions with similar offensive structure, allowing for efficient search and exploration of the entire database of player-tracking data. We show that our model finds repeated offensive structure in teams (e.g. strategy), providing a much more sophisticated, yet interpretable lens into basketball player-tracking data. This is joint work with Andrew Miller.
Luke Bornn is currently Vice President, Strategy and Analytics for the Sacramento Kings. Prior to joining the Kings, Bornn served as Head of Analytics for A.S. Roma of the Italian Serie A Football League, where he worked closely with managers, coaches and sports scientists to measure and evaluate athletes and performance. In addition to his work with soccer and basketball teams, the British Columbia native has previously held tenure-track professorships in Statistics at both Harvard University and Simon Fraser University. Bornn is a frequent contributor to the field of sports analytics, authoring research articles for the Journal for Quantitative Analysis, the Annals of Applied Statistics and the Journal of the American Statistical Association amongst others. He has published over 15 papers at the MIT Sloan sports analytics conference, including finalist selections in 2014, 2015, 2016, 2017, 2018, and 2019.