Sign In

Communications of the ACM

ACM TechNews

'moneyball' For Basketball: Using Science to Change the Nba

View as: Print Mobile App Share:
Basketball players

Boris Diaw of the San Antonio Spurs shoots as Oklahoma City Thunder's Kendrick Perkins and Serge Ibaka defend the basket during Game 5 in the NBA Western Conference finals.

Credit: Eric Gay, Associated Press

University of Southern California (USC) researchers are using SportVU optical tracking data, which uses video cameras installed in participating basketball arenas to capture real-time video footage, to compile more than one million data records per game to analyze basketball games.

The data is run through image-processing algorithms, which can analyze spatial dynamics, basketball trajectories, player velocities, and movement tracks.

The USC researchers, led by Rajiv Maheswaran and Yu-Han Chang, won best paper at the MIT Sloan Sports Analytics Conference for their work analyzing rebounding using data captured by SportVU. The researchers studied more than 11,000 shots and found that for every foot away from the basket, the chance of an offensive rebound decreases one percent until the three-point line, when it suddenly improves. The researchers concluded that in order to get offensive rebounds, players need to move much closer to the basket.

The researchers' next plan to use the SportVU data to analyze what makes good defense. Chang says it is challenging to transform the massive amount of data into something that can be applied to algorithms and used to discern patterns.

From USC News
View Full Article

Abstracts Copyright © 2012 Information Inc. External Link, Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account