Intelligent systems for analyzing soccer games: The weighted centroid

Abstract

New, intelligent systems have been developed recently to improve the quality of match analysis. These systems analyze the tactical behavior of the teams. However, the existing methods leave room for improvement. Thus, the main goal of this study is to refine the team centroid metric by considering all of the players on the team and the ball position. Furthermore, this study analyzes the relationship between the centroids of the two opposing teams. One 11-on-11 soccer match was analyzed to test the new centroid algorithm. The results provided strong evidence of the positive relation between the centroids of the two teams over time in the ‫-ݔ‬axis ‫ݎ(‬ ௦ = 0.781) and the ‫-ݕ‬axis ‫ݎ(‬ ௦ = 0.707). This study confirmed the results of previous studies that analyzed the relationship between team centroids. Furthermore, it was possible to prove the effectiveness of the new tactical metric and its relevance for adding information during a match.Keywords: Match Analysis, Soccer, Tactics, Collective Behavior, Centroid. RESUMENNuevos sistemas inteligentes se han desarrollado recientemente, con el fin de mejorar la calidad de análisis del partido. Estos sistemas basan su análisis en el comportamiento táctico de los equipos, sin embargo, todos los métodos innovadores necesitan algunos cambios para aumentar su potencial en las implicaciones prácticas. Por lo tanto, el objetivo principal de este trabajo es proponer una actualización del centroide y métrica del equipo, teniendo en cuenta a todos los jugadores del equipo y también la posición de la bola, además, tiene como objetivo analizar la relación entre los centroides de los equipos oponentes. Un partido de fútbol 11, fue analizado con el fin de aplicar el nuevo algoritmo del centroide; los principales resultados mostraron una fuerte evidencia de la relación positiva entre centroides en el eje x ‫ݎ(‬ ௦ = 0.781) y el eje y ‫ݎ(‬ ௦ = 0.707). Este estudio, confirma trabajos previos que analizaron la relación positiva y fuerte entre equipos centroides. Además, fue posible demostrar la pertinencia de la nueva actualización de métrica táctica y su importancia para el aumento de la información en las aplicaciones prácticas durante el partido.Palabras clave: análisis del partido de fútbol, táctica, comportamiento colectivo y Centroide.

What Performance Analysts Need to Know About Research Trends in Association Football (2012–2016): A Systematic Review

“…In most cases, an in-phase relationship between the competing teams' centre values during competitive performance has been investigated [26,27,61]. The study of elite European soccer suggested that team centroids moved synchronously both up and across the pitch [26].…”

The forest through the trees: Making sense of an ecological dynamics approach to measuring and developing collective behaviour in football

“…Weighted centroids account for the relative positioning of the ball, i.e. if the ball is closer to an individual, their position will be more relevant (63).…”

“…It is evident that opposing teams, regardless of whether their possessional status is attack or defence, use the positioning of the ball as a key informational variable to guide behaviour (99). Further, a plethora of existing research indicates a higher level of synchronicity in the longitudinal direction than in the lateral direction (16,63,65,72,73,78,82,99,103). This may be due to off-side constraints, limiting attacker's positioning relative to the defenders, and the position of the goals (99), with the primary attacking objective to advance up the field to create goal-scoring opportunities (73).…”

“…Despite different displacements of players, centroids can remain in the same relative position. For example, each player four metres apart will have the same relative effect on a centroid measure as if they were eight metres apart (63). Additionally, while providing useful information on a global scale, utilising centroid measures neglects to provide a complete understanding of the strategic distribution of players on the field (65).…”

Performance Analysis Tool for network analysis on team sports: A case study of FIFA Soccer World Cup 2014

“…Moreover, it is now possible to measure teammates’ cooperation and synchronization and to classify patterns of play and organizational dynamics. 16 Computational metrics such as w Centroid, 17 w Stretch Index, 18 Sectorial Lines, 19 Territorial Domain, 20 Attacking Definition Zone 21 and Defensive Play Area 4 were developed in the last 5 years.…”