Decomposing the Immeasurable Sport: A deep learning expected possession value framework for soccer
Decomposing the Immeasurable Sport: A deep learning expected possession value framework for soccer
复制标题
分解不可估量的运动：深度学习足球预期控球价值框架
DOI：
--
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Javier Fernández
中科院分区：
文献类型：
--
作者：
Javier Fernández
如何正确看待足球分析？这项运动是关于测量事件，如传球和进球，控球率和旅行距离，或甚至更抽象的概念，如错误（引用克鲁伊夫，“足球是一个游戏的错误，谁使更少的胜利”）？到目前为止，分析工作主要集中在这项运动的这些更孤立的方面，而教练则倾向于关注球场上所有22名球员的战术相互作用。足球分析缺乏一种全面的方法，可以开始解决与比赛语言更接近的性能相关的问题。问题是：谁创造了更多的价值？如何以及在哪里实现这种增值？团队成员是否在创造价值空间？什么时候以及如何进行向后传球？团队进攻策略的风险有多大？什么是球员的决策能力？
What is the right way to think about analytics in soccer? Is the sport about measured events such as passes and goals, possession percentages and traveled distance, or even more abstract notions such as mistakes (to quote Cruyff, “Soccer is a game of mistakes, whoever makes the fewer wins”)? Analytical work to date has focused primarily on these more isolated aspects of the sport, while coaches tend to focus on the tactical interplay of all 22 players on the pitch. Soccer analytics is lacking from a comprehensive approach that can start to address performance-related questions that are closer to the language of the game. Questions such as: who adds more value? How and where is this value added? Are the teammates creating spaces of value? When and how should a backward pass be taken? How risky is a team attacking strategy? What is a player’s decisionmaking profile?