There has been rapid growth in the collection of player tracking data in recent years. These data, providing spatiotemporal locations of players and ball at high resolution, have spurred methodological developments in a range of sports. There have been impacts in the development of player performance measurement (e.g., distance traveled) and in the attribution of value to specific plays (e.g., expected points from a given position) or even specific actions within a play. This review highlights key methodological contributions via statistical and machine learning approaches. The studies and outcomes discussed show how sports can be a playground for extending analytical techniques in a range of areas. The review also describes the ongoing methodological challenges associated with the use of tracking data.

中文翻译：

---

运动中的球员跟踪数据


近年来，玩家跟踪数据的收集增长迅速。这些数据以高分辨率提供了球员和球的时空位置，刺激了一系列运动的方法论发展。球员表现测量的发展（例如，移动距离）和特定比赛的价值归因（例如，给定位置的预期得分）甚至比赛中的特定动作都受到了影响。本综述重点介绍了通过统计和机器学习方法的关键方法学贡献。讨论的研究和结果表明，体育如何成为在一系列领域扩展分析技术的游乐场。本综述还描述了与跟踪数据使用相关的持续方法挑战。