Competition-Wide Evaluation of Individual and Team Movements in Soccer

Laszlo Gyarmati, Mohamed Hefeeda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

It is challenging to get access to datasets related to the physical performance of soccer players. The teams consider such information highly confidential, especially if it covers in-game performance. Hence, most analysis and evaluation of the players' performance do not contain much information on the physical aspect of the game. We propose a novel method to solve this issue by deriving individual and team movements in soccer. We use event-based datasets allowing us to analyze the movement profiles of potentially tens of thousands of players. By analyzing the similarity of players based on their movements we find that C. Ronaldo and Ruben Castro were extremely similar despite having two orders of magnitude in their market values, 29 players are more similar to Ronaldo than the most similar counterpart of Messi based on the consistency and uniqueness of their trajectories, and that teams use an abundance of unique attacking schemes, 8909 unique attacks were launched in the 2012/13 season of the Spanish league. Our study reveals novel, actionable insights for the soccer industry at an unprecedented scale.

Original languageEnglish
Title of host publicationProceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016
PublisherIEEE Computer Society
Pages144-151
Number of pages8
ISBN (Electronic)9781509054725
DOIs
Publication statusPublished - 30 Jan 2017
Event16th IEEE International Conference on Data Mining Workshops, ICDMW 2016 - Barcelona, Spain
Duration: 12 Dec 201615 Dec 2016

Other

Other16th IEEE International Conference on Data Mining Workshops, ICDMW 2016
CountrySpain
CityBarcelona
Period12/12/1615/12/16

Fingerprint

Trajectories
Industry

Keywords

  • Football
  • Movements
  • Soccer
  • Sport analytics

ASJC Scopus subject areas

  • Computer Science Applications
  • Software

Cite this

Gyarmati, L., & Hefeeda, M. (2017). Competition-Wide Evaluation of Individual and Team Movements in Soccer. In Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016 (pp. 144-151). [7836659] IEEE Computer Society. https://doi.org/10.1109/ICDMW.2016.0028

Competition-Wide Evaluation of Individual and Team Movements in Soccer. / Gyarmati, Laszlo; Hefeeda, Mohamed.

Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society, 2017. p. 144-151 7836659.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gyarmati, L & Hefeeda, M 2017, Competition-Wide Evaluation of Individual and Team Movements in Soccer. in Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016., 7836659, IEEE Computer Society, pp. 144-151, 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016, Barcelona, Spain, 12/12/16. https://doi.org/10.1109/ICDMW.2016.0028
Gyarmati L, Hefeeda M. Competition-Wide Evaluation of Individual and Team Movements in Soccer. In Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society. 2017. p. 144-151. 7836659 https://doi.org/10.1109/ICDMW.2016.0028
Gyarmati, Laszlo ; Hefeeda, Mohamed. / Competition-Wide Evaluation of Individual and Team Movements in Soccer. Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016. IEEE Computer Society, 2017. pp. 144-151
@inproceedings{4d78a4f0464140c986f946c11f51f309,
title = "Competition-Wide Evaluation of Individual and Team Movements in Soccer",
abstract = "It is challenging to get access to datasets related to the physical performance of soccer players. The teams consider such information highly confidential, especially if it covers in-game performance. Hence, most analysis and evaluation of the players' performance do not contain much information on the physical aspect of the game. We propose a novel method to solve this issue by deriving individual and team movements in soccer. We use event-based datasets allowing us to analyze the movement profiles of potentially tens of thousands of players. By analyzing the similarity of players based on their movements we find that C. Ronaldo and Ruben Castro were extremely similar despite having two orders of magnitude in their market values, 29 players are more similar to Ronaldo than the most similar counterpart of Messi based on the consistency and uniqueness of their trajectories, and that teams use an abundance of unique attacking schemes, 8909 unique attacks were launched in the 2012/13 season of the Spanish league. Our study reveals novel, actionable insights for the soccer industry at an unprecedented scale.",
keywords = "Football, Movements, Soccer, Sport analytics",
author = "Laszlo Gyarmati and Mohamed Hefeeda",
year = "2017",
month = "1",
day = "30",
doi = "10.1109/ICDMW.2016.0028",
language = "English",
pages = "144--151",
booktitle = "Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Competition-Wide Evaluation of Individual and Team Movements in Soccer

AU - Gyarmati, Laszlo

AU - Hefeeda, Mohamed

PY - 2017/1/30

Y1 - 2017/1/30

N2 - It is challenging to get access to datasets related to the physical performance of soccer players. The teams consider such information highly confidential, especially if it covers in-game performance. Hence, most analysis and evaluation of the players' performance do not contain much information on the physical aspect of the game. We propose a novel method to solve this issue by deriving individual and team movements in soccer. We use event-based datasets allowing us to analyze the movement profiles of potentially tens of thousands of players. By analyzing the similarity of players based on their movements we find that C. Ronaldo and Ruben Castro were extremely similar despite having two orders of magnitude in their market values, 29 players are more similar to Ronaldo than the most similar counterpart of Messi based on the consistency and uniqueness of their trajectories, and that teams use an abundance of unique attacking schemes, 8909 unique attacks were launched in the 2012/13 season of the Spanish league. Our study reveals novel, actionable insights for the soccer industry at an unprecedented scale.

AB - It is challenging to get access to datasets related to the physical performance of soccer players. The teams consider such information highly confidential, especially if it covers in-game performance. Hence, most analysis and evaluation of the players' performance do not contain much information on the physical aspect of the game. We propose a novel method to solve this issue by deriving individual and team movements in soccer. We use event-based datasets allowing us to analyze the movement profiles of potentially tens of thousands of players. By analyzing the similarity of players based on their movements we find that C. Ronaldo and Ruben Castro were extremely similar despite having two orders of magnitude in their market values, 29 players are more similar to Ronaldo than the most similar counterpart of Messi based on the consistency and uniqueness of their trajectories, and that teams use an abundance of unique attacking schemes, 8909 unique attacks were launched in the 2012/13 season of the Spanish league. Our study reveals novel, actionable insights for the soccer industry at an unprecedented scale.

KW - Football

KW - Movements

KW - Soccer

KW - Sport analytics

UR - http://www.scopus.com/inward/record.url?scp=85015159806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015159806&partnerID=8YFLogxK

U2 - 10.1109/ICDMW.2016.0028

DO - 10.1109/ICDMW.2016.0028

M3 - Conference contribution

AN - SCOPUS:85015159806

SP - 144

EP - 151

BT - Proceedings - 16th IEEE International Conference on Data Mining Workshops, ICDMW 2016

PB - IEEE Computer Society

ER -