A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system

Fuente: Redalyc
Saved in:
Bibliographic Details
Main Author: César Soto-Valero
Format: Artículo científico
Language:en
Published: Editorial Ramón Cantó Alcaraz 2017
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1876429378222555136
author César Soto-Valero
author_facet César Soto-Valero
contents A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system César Soto-Valero Multidisciplinarias (Ciencias Sociales) machine learning Association football principal component analysis Gaussian mixture clustering models classification and regression trees The generation and availability of football data has increased considerably last decades, mostly due to its popularity and also because of technological advances. Gaussian mixture clustering models represents a novel approach to exploring and analyzing performance data in sports. In this paper, we use principal com- ponents analysis in conjunction with a model-based Gaussian clustering method with the purpose of charac- terizing professional football players. Our model approach is tested using 40 attributes from EA Sports' FIFA video game series system, corresponding to 7705 European players. Clustering results reveal a clear dis- tinction among different performance indicators, representing four different roles in the team. Players were labeled according to these roles and a gradient tree boosting model was used for ranking attributes regar- ding to its importance. We found that the dribbling skill is the most discriminating variable among the diffe- rent clustered players’ profiles. 2017 artículo científico 1885-3137 https://www.redalyc.org/articulo.oa?id=71051616004 https://www.redalyc.org/journal/710/71051616004/ https://www.redalyc.org/journal/710/71051616004/html/ https://www.redalyc.org/journal/710/71051616004/71051616004.epub https://www.redalyc.org/journal/710/71051616004/movil en http://www.redalyc.org/revista.oa?id=710 RICYDE. Revista Internacional de Ciencias del Deporte application/pdf Editorial Ramón Cantó Alcaraz RICYDE. Revista Internacional de Ciencias del Deporte (España) Num.49 Vol.XIII
format Artículo científico
id redalyc_71051616004
institution Redalyc
language en
publishDate 2017
publisher Editorial Ramón Cantó Alcaraz
spellingShingle A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system
César Soto-Valero
Multidisciplinarias (Ciencias Sociales)
machine learning
Association football
principal component analysis
Gaussian mixture clustering models
classification and regression trees
A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system César Soto-Valero Multidisciplinarias (Ciencias Sociales) machine learning Association football principal component analysis Gaussian mixture clustering models classification and regression trees The generation and availability of football data has increased considerably last decades, mostly due to its popularity and also because of technological advances. Gaussian mixture clustering models represents a novel approach to exploring and analyzing performance data in sports. In this paper, we use principal com- ponents analysis in conjunction with a model-based Gaussian clustering method with the purpose of charac- terizing professional football players. Our model approach is tested using 40 attributes from EA Sports' FIFA video game series system, corresponding to 7705 European players. Clustering results reveal a clear dis- tinction among different performance indicators, representing four different roles in the team. Players were labeled according to these roles and a gradient tree boosting model was used for ranking attributes regar- ding to its importance. We found that the dribbling skill is the most discriminating variable among the diffe- rent clustered players’ profiles. 2017 artículo científico 1885-3137 https://www.redalyc.org/articulo.oa?id=71051616004 https://www.redalyc.org/journal/710/71051616004/ https://www.redalyc.org/journal/710/71051616004/html/ https://www.redalyc.org/journal/710/71051616004/71051616004.epub https://www.redalyc.org/journal/710/71051616004/movil en http://www.redalyc.org/revista.oa?id=710 RICYDE. Revista Internacional de Ciencias del Deporte application/pdf Editorial Ramón Cantó Alcaraz RICYDE. Revista Internacional de Ciencias del Deporte (España) Num.49 Vol.XIII
title A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system
topic Multidisciplinarias (Ciencias Sociales)
machine learning
Association football
principal component analysis
Gaussian mixture clustering models
classification and regression trees
url https://www.redalyc.org/articulo.oa?id=71051616004
https://www.redalyc.org/journal/710/71051616004/
https://www.redalyc.org/journal/710/71051616004/html/
https://www.redalyc.org/journal/710/71051616004/71051616004.epub
https://www.redalyc.org/journal/710/71051616004/movil