Scholarlink

This article presents a study of the application of the decision tree method for analyzing basketball statistics in order to identify key factors affecting the player’s utility coefficient. The study was conducted on the basis of a publicly available set of NBA player statistics for the 1997–1998 season. The study of the distribution of input data showed the presence of diversity in the characteristics of the players. An analysis of the importance of features using a decision tree revealed that the most important factors are “Time”, “Losses”, “Rebounds”, “Positions”, “Times. transfers” and “Points”. The removal of less significant features led to an improvement in the accuracy of the model. The results of the study confirm the effectiveness of the decision tree method for analyzing basketball statistics and demonstrate the importance of using machine learning in sports. The knowledge gained can be applied by coaches, scouts and club managers to better evaluate players and plan training sessions.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Analysis of Sports Statistics Using a Hierarchical Model in the Form of a Decision Tree Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Vadim S. Tynchenko,
  • Svetlana V. Kukartseva,
  • Kirill I. Kravtsov,
  • Danil A. Tkachenko

摘要

This article presents a study of the application of the decision tree method for analyzing basketball statistics in order to identify key factors affecting the player’s utility coefficient. The study was conducted on the basis of a publicly available set of NBA player statistics for the 1997–1998 season. The study of the distribution of input data showed the presence of diversity in the characteristics of the players. An analysis of the importance of features using a decision tree revealed that the most important factors are “Time”, “Losses”, “Rebounds”, “Positions”, “Times. transfers” and “Points”. The removal of less significant features led to an improvement in the accuracy of the model. The results of the study confirm the effectiveness of the decision tree method for analyzing basketball statistics and demonstrate the importance of using machine learning in sports. The knowledge gained can be applied by coaches, scouts and club managers to better evaluate players and plan training sessions.