Original title: Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science
Older soccer analysis often used observations that left out much of the match context. New tracking tools and small sensors can collect detailed records of player movements and physical performance, but the sheer volume is hard to use. This paper discusses how big-data tools and machine learningComputer methods that use data to find patterns or make predictions. might help researchers study tactical decisions. It also proposes a technology setup and says data access and governance need attention.
Imagine trying to plan a team dinner when everyone has a different schedule, appetite, and food preference. A few notes leave out key details, but collecting every detail can create a pile too large to sort through. In this paper, the dinner details stand for information about players and team play, while the pile represents the challenge of making useful sense of all that information.
Coaches and sports scientists want to understand how players’ skills, physical performance, and team shape combine during play. More detailed tracking could help answer that, but only if researchers can handle the data and gain access to it.
The abstract describes a discussion and a proposed technology stack; it does not report tests showing that the approach improves tactical analysis or establishes a validated model of decision making. It also notes that data access and governance obstacles must be overcome.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Big data and tactical analysis in elite soccer: future challenges and opportunities for sports science — Robert Rein, Daniel Memmert — SpringerPlus — doi:10.1186/s40064-016-3108-2
Abstract licence: CC BY
Explanation generated by Synthesis from the abstract — it is not the original paper.