Unlocking the potential of big data to support tactical performance analysis in professional soccer: A systematic review

Abstract

In professional soccer, increasing amounts of data are collected that harness great potential when it comes to analysing tactical behaviour. Unlocking this potential is difficult as big data challenges the data management and analytics methods commonly employed in sports. By joining forces with computer science, solutions to these challenges could be achieved, helping sports science to find new insights, as is happening in other scientific domains. We aim to bring multiple domains together in the context of analysing tactical behaviour in soccer using position tracking data. A systematic literature search for studies employing position tracking data to study tactical behaviour in soccer was conducted in seven electronic databases, resulting in 2338 identified studies and finally the inclusion of 73 papers. Each domain clearly contributes to the analysis of tactical behaviour, albeit insometimes radicallydifferent ways. Accordingly, we present a multidisciplinary framework where each domain's contributions to feature construction, modelling and interpretation can be situated. We discuss a set of key challenges concerning the data analytics process, specifically feature construction, spatial and temporal aggregation. Moreover, we discuss how these challenges could be resolved through multidisciplinary collaboration, which is pivotal in unlocking the potential of position tracking data in sports analytics.

Attacking Key Performance Indicators in Soccer: Current Practice and Perceptions from the Elite to Youth Academy Level

“…These efforts represent progress, but collaboration and education between practitioners and scientists must continue to go both ways. The interplay between computer science experts who can handle the vast amounts of data, and domain experts who can address the right questions, is a challenging task (Goes et al, 2020). Increased multi-disciplinary approaches including research groups and sports scientists competent in soccer will continue to be necessary to optimize KPI development and application.…”

“…video analysis) over quantitative approaches (Nelson and Groom, 2012). In opposition to these preferences, there has been an exponential increase in the human capital invested in soccer research and analytics in recent years (Goes et al, 2020;Rein and Memmert, 2016a). This indicates that different stakeholders of a club or federation value, use, and implement KPIs differently.…”

A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer)

“…The total number of goals scored over the whole season per team and player is displayed in black. Now that the amount of data-driven approaches to support tactical analysis in football is increasing (Goes et al, 2020), more qualitative studies might help to underpin the statistical evaluation of models like xG. Although we present a first attempt toward an expert-based evaluation of our approaches (see sections 3.2 and 4.4), there is a lot of potential for further investigations, which could also serve to establish data-driven methods in the sport science and football community.…”

Big Data and Analytics in Sport Management

“…Most of the articles in this area are published within industry outlets, discussing the increased use of analytics in sport and the need for more data-driven decision making within sport organizations (Szymanski, 2020). The academic literature in this area has focused primarily on big data and on-field performance (Goes et al, 2020;Morgulev, Azar, & Lidor, 2018;Van den Berg, Coetzee, & Mearns, 2020) with less attention dedicated to big data and sport business (Hutchins, 2016;Millington & Millington, 2015) and overarching discussions of analytics in the field (Spaaij & Thiel, 2017;Szymanski, 2020). As big data has evolved in sport, this literature has become critical to our understanding of the role of sport analytics and its impact on various aspects of the industry.…”