Understanding the evolution of the skills of football players through the scores of the FIFA electronic game
Abstract
The popularity of football generates interest in characterizing the development of elite players, whether for commercial or entertainment reasons. EA Sports, producer of the FIFA electronic games franchise, invests in evaluating athletes to represent them in a realistic way. In this article, the scores attributed in multiple updates as longitudinal measurements are studied and the possibility of describing the development curves through a relatively small number of patterns is evaluated. A transformation of the measurement series is proposed, which aims to emphasize formats and cluster analysis techniques are used in the observations, namely k-means and Spectral Clustering. The results for multiple skills of players in different groups of positions are evaluated and 11 Evolution Patterns identified in the groupings are presented. The Average Silhouette Width index is used.
Keywords:
clustering, data mining, sports analytics
References
Akhanli, S. E. and Hennig, C. Some issues in distance construction for football players performance data. Archives of Data Science 2 (1), 2017.
Caiado, J., Maharaj, E., and D’urso, P. Time series clustering. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 241–263, 2016.
Cotta, L., de Melo, P. O. V., Benevenuto, F., and Loureiro, A. A. Using fifa soccer video game data for soccer analytics. In Proceedings of the KDD Workshop on Large-Scale Sports Analytics. San Francisco, USA, 2016.
Eirola, E., Doquire, G., Verleysen, M., and Lendasse, A. Distance estimation in numerical data sets with missing values. Information Sciences vol. 240, pp. 115–128, 2013.
Halkidi, M., Vazirgiannis, M., and Hennig, C. Method-independent indices for cluster validation and estimating the number of clusters. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 595–618, 2016.
McFee, B. and Ellis, D. Analyzing song structure with spectral clustering. In ISMIR. pp. 405–410, 2014.
Meila, M. Spectral Clustering. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 147–164, 2016.
Paparrizos, J. and Gravano, L. Fast and accurate time-series clustering. ACM Transactions on Database Systems 42 (2): 8, 2017.
Reagan, A. J., Mitchell, L., Kiley, D., Danforth, C. M., and Dodds, P. S. The emotional arcs of stories are dominated by six basic shapes. EPJ Data Science 5 (1): 31, 2016.
Sardá-Espinosa, A. Comparing time-series clustering algorithms in r using the dtwclust package. [link], 2017.
Soto-Valero, C. A Gaussian mixture clustering model for characterizing football players using the EA Sports’ FIFA video game system. RICYDE. Revista Internacional de Ciencias del Deporte 13 (49): 244–259, 2017.
Von Luxburg, U. A tutorial on spectral clustering. Statistics and computing 17 (4): 395–416, 2007.
Vroonen, R., Decroos, T., Van Haaren, J., and Davis, J. Predicting the potential of professional soccer players. In Machine Learning and Data Mining for Sports Analytics ECML/PKDD 2017 workshop. Skopje, Macedonia, 2017.
Caiado, J., Maharaj, E., and D’urso, P. Time series clustering. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 241–263, 2016.
Cotta, L., de Melo, P. O. V., Benevenuto, F., and Loureiro, A. A. Using fifa soccer video game data for soccer analytics. In Proceedings of the KDD Workshop on Large-Scale Sports Analytics. San Francisco, USA, 2016.
Eirola, E., Doquire, G., Verleysen, M., and Lendasse, A. Distance estimation in numerical data sets with missing values. Information Sciences vol. 240, pp. 115–128, 2013.
Halkidi, M., Vazirgiannis, M., and Hennig, C. Method-independent indices for cluster validation and estimating the number of clusters. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 595–618, 2016.
McFee, B. and Ellis, D. Analyzing song structure with spectral clustering. In ISMIR. pp. 405–410, 2014.
Meila, M. Spectral Clustering. In C. Hennig, M. Meila, F. Murtagh, and R. Rocci (Eds.), Handbook of Cluster Analysis. CRC Press, USA, pp. 147–164, 2016.
Paparrizos, J. and Gravano, L. Fast and accurate time-series clustering. ACM Transactions on Database Systems 42 (2): 8, 2017.
Reagan, A. J., Mitchell, L., Kiley, D., Danforth, C. M., and Dodds, P. S. The emotional arcs of stories are dominated by six basic shapes. EPJ Data Science 5 (1): 31, 2016.
Sardá-Espinosa, A. Comparing time-series clustering algorithms in r using the dtwclust package. [link], 2017.
Soto-Valero, C. A Gaussian mixture clustering model for characterizing football players using the EA Sports’ FIFA video game system. RICYDE. Revista Internacional de Ciencias del Deporte 13 (49): 244–259, 2017.
Von Luxburg, U. A tutorial on spectral clustering. Statistics and computing 17 (4): 395–416, 2007.
Vroonen, R., Decroos, T., Van Haaren, J., and Davis, J. Predicting the potential of professional soccer players. In Machine Learning and Data Mining for Sports Analytics ECML/PKDD 2017 workshop. Skopje, Macedonia, 2017.
Published
2018-10-22
How to Cite
SOARES JR., Ivan R.; ASSUNÇÃO, Renato M.; VAZ DE MELO, Pedro O. S..
Understanding the evolution of the skills of football players through the scores of the FIFA electronic game. In: SYMPOSIUM ON KNOWLEDGE DISCOVERY, MINING AND LEARNING (KDMILE), 6. , 2018, São Paulo/SP.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2018
.
p. 121-128.
ISSN 2763-8944.
DOI: https://doi.org/10.5753/kdmile.2018.27393.
