Communications of the ACM
Disney Research Builds Computer Models to Analyze Play in Pro Basketball and Soccer
Data-driven methods can serve as tools for educating players on opponents' tendencies.
Credit: Pinterest
Disney researchers used player-tracking data from more than 600 basketball games from the 2012-13 National Basketball Association (NBA) season to develop models that can make accurate in-game predictions of what each player is likely to do next in a game situation.
In a separate study, Disney researchers collected more than 400 million data points from a professional soccer league to examine team behavior rather than individual players. The researchers showed they could accurately detect and visualize team formations well enough to identify teams based just on their style of play 70 percent of the time.
Disney Research associate research scientist Patrick Lucey says these automated, data-driven methods can serve as tools for educating players in the limited time available for practice, or as tools for scouting opposition teams and planning for specific game situations.
In the NBA study, the researchers used a machine-learning approach in which the models were trained based on the tendencies of each player to take shots or pass or receive passes in certain locations. In the soccer study, the researchers developed a "role-based" representation of teams that does not track individuals but instead automatically identifies the players in each position and how they play that position.
From EurekAlert
View Full Article
Abstracts Copyright © 2014 Information Inc., Bethesda, Maryland, USA
No entries found