Modeling offensive player movement in professional basketball

Abstract

The 2013 arrival of SportVU player tracking data in all NBA arenas introduced an overwhelming amount of on-court information -information which the league is still learning how to maximize for insights into player performance and basketball strategy. Knowing where the ball and every player on the court are at all times throughout the course of the game produces almost endless possibilities, and it can be difficult figuring out where to begin. This article serves as a step-by-step guide for how to turn a data feed of one million rows of SportVU data from one NBA game into visualizable components you can use to model any player's movement. We detail some utility functions that are helpful for manipulating SportVU data before applying it to the task of visualizing player offensive movement. We conclude with visualizations of the resulting output for one NBA game, as well as what the results look like aggregated across an entire season for three NBA stars with very different offensive tendencies.

A Method of Using Data Mining and Edge Computing to Calculate the Standing Efficiency of Basketball Games

“…Take a basketball game as an example. A basketball game is divided into four quarters, and each quarter consists of several defensive and offensive rounds of players from both sides of the game [6].…”

Filtering Procedures for Sensor Data in Basketball

“…The novelty of this procedure is that, unlike existing works, for example [16], it works when the ball's trajectory is unavailable. However, further research is to be planned in order to validate the algorithm also with respect to a visual analysis of the same match.…”

“…To do that we make use of available sensor data tracked during a game. This work is similar to that by [16], as they provide a procedure to process ball's and players' trajectories. However, our procedure differs, since it works even if data on ball's movement is missing.…”

Analysis of professional basketball field goal attempts via a Bayesian matrix clustering approach

“…Conventional statistical research for sports analytics was mainly concerned with forecasting the game results, such as predicting the number of goals scored in soccer matches (Dixon and Coles, 1997;Karlis and Ntzoufras, 2003;Baio and Blangiardo, 2010), and the basketball game outcomes (Carlin, 1996;Caudill, 2003;Cattelan et al, 2013). More recently, fast development in player tracking technologies has greatly facilitated the data collection (Albert et al, 2017), and in turn substantially expanded the role of statistics in sports analytics, including granular evaluation of player/team performance (Cervone et al, 2014;Franks et al, 2015;Cervone et al, 2016;Wu and Bornn, 2018), and in-game strategy evaluation (Fernandez and Bornn, 2018;Sandholtz et al, 2019).…”