Caracterização de Estratégias de Futebol com base na Frequência, Importância e Efetividade de Jogadas

• Gabriel Valadao Federal University of Minas Gerais
• João L. L. Gonçalves Federal University of Minas Gerais
• João L. L. Megale Federal University of Minas Gerais
• Vinicius M. Paula Federal University of Minas Gerais
• Hugo Rios-Neto Federal University of Minas Gerais
• Adriano C. M. Pereira Federal University of Minas Gerais
• Wagner Meira Jr. Federal University of Minas Gerais

DOI: https://doi.org/10.5753/eniac.2023.234936

Abstract

Understanding and predicting soccer results is a challenge due to the complexity of the game itself, the number and diversity of players involved and even external factors that are not always qualifiable or quantifiable. On the other hand, there is a significant effort to train teams and prepare them to act and react appropriately to a variety of scenarios, which indicates the existence of strategies. This paper aims to characterize these football strategies, focusing on how the team behaves collectively. We define football strategy as a set of moves that must be frequent, important and effective, which are normally conflicting criteria. We propose a methodology to identify these strategies, which is implemented and evaluated using real data from league seasons. The results show that our methodology allows characterizing the strategies of different teams.

Keywords: data mining, machine learning, data science applied to soccer

References

Davis, J., Bransen, L., Devos, L., Meert, W., Robberechts, P., Van Haaren, J., and Van Roy, M. (2022). Evaluating sports analytics models: Challenges, approaches, and lessons learned. In AI Evaluation Beyond Metrics Workshop at IJCAI 2022, volume 3169, pages 1–11. CEUR Workshop Proceedings.

Decroos, T., Bransen, L., Van Haaren, J., and Davis, J. (2019). Actions speak louder than goals: Valuing player actions in soccer. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, pages 1851–1861.

Decroos, T., Roy, M. V., and Davis, J. (2020). Soccermix: Representing soccer actions with mixture models. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 459–474. Springer.

Decroos, T., Van Haaren, J., and Davis, J. (2018). Automatic discovery of tactics in spatio-temporal soccer match data. In Proceedings of the 24th ACM 14 SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 223–232.

Ensum, J., Pollard, R., and Taylor, S. (2004). Applications of logistic regression to shots at goal in association football: Calculation of shot probabilities, quantification of factors and player/team. Journal of Sports Sciences, 22(6):500–520.

Fernández, J., Bornn, L., and Cervone, D. (2021). A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions. Machine Learning, 110(6):1389–1427.

Godfrey, P., Shipley, R., and Gryz, J. (2007). Algorithms and analyses for maximal vector computation. The VLDB Journal, 16(1):5–28.

Green, S. (2012). Assessing the performance of premier league goalscorers. OptaPro Blog.

Harper, J. (2021). Data experts are becoming football’s best signings. BBC News.

Malqui, J. L. S., Romero, N. M. L., Garcia, R., Alemdar, H., and Comba, J. L. (2019). How do soccer teams coordinate consecutive passes? a visual analytics system for analysing the complexity of passing sequences using soccer flow motifs. Computers & Graphics, 84:122–133.

McCarthy, C., Tampakis, P., Chiarandini, M., Randers, M. B., Jänicke, S., and Zimek, A. (2023). Analyzing passing sequences for the prediction of goal-scoring opportunities. In Machine Learning and Data Mining for Sports Analytics: 9th International Workshop, MLSA 2022, Grenoble, France, September 19, 2022, Revised Selected Papers, pages 27–40. Springer.

Pappalardo, L., Cintia, P., Rossi, A., Massucco, E., Ferragina, P., Pedreschi, D., and Giannotti, F. (2019). A public data set of spatio-temporal match events in soccer competitions. Scientific data, 6(1):236.

Pei, J., Han, J., Mortazavi-Asl, B., Wang, J., Pinto, H., Chen, Q., Dayal, U., and Hsu, M. (2004). Mining sequential patterns by pattern-growth: The prefixspan approach. IEEE Trans. Knowl. Data Eng., 16(11):1424–1440.