Evaluating Player Interaction and Performance using Network Analysis

In professional sports, a team's biggest concern is winning a game every time they step on the pitch. All teams aspire to give their best effort during a game, and doing so necessitates taking into account players interaction with their teammates during playing time. Therefore, determining each players interaction and evaluating their performance plays an important role in basketball. The study reviewed and evaluated players interaction for the 2017/2018 NBA season. Though there are known techniques for analysis and player performance evaluation which have been developed overtime, several other techniques have been proposed. However, in order to better manage the game and positioning of players, network analysis a better way to understand players preference in passing the ball to other players. The study used Network analysis to assess and analyze basketball players interaction and general performance. Statistics for every player for 2017/2018 season were gathered by scraping data from Basketball-Reference and used custom R scripts to gather box score data from basketball reference. Precisely there were 30 teams and had initially 23 variables related to their performance with attributes such as fields goals made, field goals made, points scored with field goals, points scored and so on. Network nodes for each players assist performance was highlighted. Network diagram were then generated for different teams such as Milwaukee Bucks, Cleveland which shown the consistency of passes for each player and interaction.