Title :
Analysis of offense tactics of basketball games using link prediction
Author :
Tao Zhang ; Gongzhu Hu ; Qi Liao
Author_Institution :
Dept. of Comput. Sci., Central Michigan Univ., Mount Pleasant, MI, USA
Abstract :
Every basketball game has a lot of game records, also called match data. All the data are not only statistical but also logical and spatial. People normally use these kind of data to obtain statistical or summarized information of the games, but few have used these data to analyze the teams´ tactics. In this paper, we present an approach to analyze the match data for detecting basketball teams´ tactic using link prediction method. The main idea is to create a measure for the team offense tactics based on the Basketball Analysis Graph (BA graph) and use link prediction to extract the information about the cooperation between teammates and offense priority. The information may be used for basketball game strategy assistance.
Keywords :
graph theory; social networking (online); sport; basketball analysis graph; basketball games; game records; link prediction; link prediction method; offense tactics analysis; social network; statistical information; summarized information; Barium; Data mining; Games; Prediction algorithms; Prediction methods; Social network services; Weight measurement; Katz measure; basketball offense tactics; game strategy assistance; link prediction; social networks;
Conference_Titel :
Computer and Information Science (ICIS), 2013 IEEE/ACIS 12th International Conference on
Conference_Location :
Niigata
DOI :
10.1109/ICIS.2013.6607842