Uso de enfoques de aprendizaje automático para predecir los resultados de los juegos: el caso de la liga nacional de fútbol sala
Resumen
The use of machine learning approaches in sports has been grown in the last decade. Sports analytics, outcome match results, and possible player’s injury are examples of machine learning applications. Accordingly, this work aims to use machine learning techniques to build models to predict FutSal National League (LNF) results (win/loss/draw) based on data collected in the first half of a match. To accomplish that, we extract the data from the LNF website, and, based on the data, we propose six new features using the concept of team strength. The data correspond to the 2016 to 2019 seasons. The models are built usimg machine learning approaches, and they are validated through an accuracy metric. We build ten models, and the predictions are organized as follows: the individual performance of each model and a voting approach (committee) based on the majority of the predicted results. The results show that the individual models get better performance when predicting a single result (e.g., home win) with 95% accuracy. On the other hand, the committee gets a better performance regarding the overall results. The win, loss, and draw results reach almost 79% accuracy.
Citas
-Anderson, C.; Sally, D.The numbers game: Why everything you know about football is wrong. Penguin UK. 2013.
-Baboota, R.; Kaur, H. Predictive analysis and modelling football results using machine learning approach for English Premier League. International Journal of Forecasting. Vol. 35. Núm. 2. 2019. p.741-755.
-Bunker, R.P.; Thabtah, F. A machine learning framework for sport result prediction. Applied computing and informatics. Vol. 15. Núm. 1. 2019. p. 27-33.
-Constantinou, A.; Fenton, N. Towards smart-data: Improving predictive accuracy in long-term football team performance. Knowledge-Based Systems. Vol. 124. 2017. p 93-104.
-Duarte, D.; Ståhl, N. Machine learning: a concise overview. In: DATA Science in Practice. Springer. 2019. p. 27-58.
-Frencken, W. G. P.; Lemmink, K. A. P. M. Team kinematics of small-sided soccer games. In: Reilly, T.; Korkusuz, F. editors. Science and Football VI. New York. Routledge. 2009. p. 161-166.
-Fried, G.; Mumcu, C.; editors. Sport analytics: A data-driven approach to sport business and management. Taylor & Francis. 2016.
-Flôres, F. S.; Santos, D. L.; Carlson, G. R.; Gelain, E. Z. What Can Coaches Do? The Relationship Between Substitution and Results of Professional Football Matches. Revista Brasileira de Futsal e Futebol. São Paulo. Vol. 11. Núm. 43. 2019. p. 215-222.
-Horvat, T.; Job, J. The use of machine learning in sport outcome prediction: A review. Wiley Interdisciplinary Reviews. Vol. 10. Núm. 5. 2020. p.e1380.
-Imai, T.; Uchiyama, A.; Magome, T.; Higashino, T. Play recognition using soccer tracking data based on machine learning. InInternational Conference on Network-Based Information Systems. Springer. Cham. 2018. p. 875-884.
-Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; Vanderplas, J. Scikit-learn: Machine learning in Python. The Journal of machine Learning research. Vol. 12. 2011. p. 2825-2830.
-Stübinger, J.; Mangold, B.; Knoll, J. Machine learning in football betting: Prediction of match results based on player characteristics. Applied Sciences. Vol. 10. Núm. 1. 2020. p.46.
-Tsunoda, T.; Komori, Y.; Matsugu, M.; Harada, T. Football action recognition using hierar-chical lstm. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Work shops (CVPRW). 2017. p. 155-163.
-Van Haaren, J.; Van den Broeck, G. Relational learning for football-related predictions. In Latest advances in inductive logic programming. 2015. p. 237-244.
Derechos de autor 2021 Denio Duarte, Jefferson Alexandre Coppini
![Creative Commons License](http://i.creativecommons.org/l/by-nc/4.0/88x31.png)
Esta obra está bajo licencia internacional Creative Commons Reconocimiento-NoComercial 4.0.
Los autores que publican en esta revista aceptan los siguientes términos:
- Los autores conservan los derechos de autor y otorgan a la revista el derecho de primera publicación, con el trabajo licenciado simultáneamente bajo la Creative Commons Attribution License BY-NC que permite compartir el trabajo con reconocimiento de la autoría del trabajo y publicación inicial en esta revista.
- Los autores están autorizados a celebrar contratos adicionales por separado, para la distribución no exclusiva de la versión del trabajo publicado en esta revista (por ejemplo, publicar en un repositorio institucional o como capítulo de un libro), con reconocimiento de autoría y publicación inicial en esta revista. .
- Se permite y se anima a los autores a publicar y distribuir su trabajo en línea (por ejemplo, en repositorios institucionales o en su página personal) en cualquier momento antes o durante el proceso editorial, ya que esto puede generar cambios productivos, así como incrementar el impacto y la cita de lo publicado. trabajar (Ver O Efeito do Acesso Livre).