Aplicación de métodos de aprendizaje automático en el análisis y la predicción de resultados deportivos (Application of automated learning methods for analyzing and predicting sports outcomes)

Autores/as

  • César Soto Valero

DOI:

https://doi.org/10.47197/retos.v0i34.58506

Palabras clave:

aprendizaje automático, datos deportivos, análisis cuantitativo, desempeño deportivo, predicción de resultados competitivos (machine learning, sport data sets, quantitative analysis, sport performance, game outcome prediction)

Resumen

El aprendizaje automático es una herramienta muy útil para el análisis de la gran cantidad de datos que se manejan en el deporte moderno. En la actualidad, este tipo de métodos se han convertido en un ámbito de investigación con grandes perspectivas de aplicación. En el presente trabajo se realiza una revisión del estado del arte sobre los principales métodos de aprendizaje automático empleados en el análisis cuantitativo de datos deportivos. En particular, se plantean las posibilidades que ofrecen estos métodos para dar solución a dos de los problemas más complejos en el deporte: el análisis del desempeño deportivo y la predicción de resultados competitivos. Además, se estudian las ventajas que ofrece el uso del aprendizaje automático para el análisis de los mercados deportivos y se propone una metodología para su aplicación como parte del proceso de toma de decisiones en el caso de las apuestas deportivas. La aplicación de esta teoría contribuye al desarrollo del análisis de datos deportivos, lo cual trae consigo una mejor comprensión del funcionamiento de las diferentes disciplinas deportivas y potencia el desarrollo técnico-táctico en el deporte. 

Abstract. Automated learning is a very useful tool for studying the vast amount of data constantly generated in modern sports. Currently, automated learning has become a field of research with a wide range of perspectives and applications. In this work, we perform a review on automated learning methods used for analyzing quantitative sport data. In particular, we focus on the advantages offered by automated learning methods to solve two of the most complex problems in sports: performance analysis, and prediction of competitive outcomes. In addition, we analyze automated learning methods used for monitoring sports markets. Furthermore, we propose a methodology for the application of automated learning methods in decision-making processes associated with sports bets. The application of this theory contributes significantly to the development of the analysis of sports data, which ensures a better understanding of the different sport disciplines and enhances technical-tactical development in sport.

Citas

Aguera, M. T., Blanco, A., Mendo, A. H., & Losada, J. L. L. (2015). Técnicas de análisis en estudios observacionales en ciencias del deporte. Cuadernos de psicología del deporte, 15(1), 13-30.

Alderson, J. (2015). A markerless motion capture technique for sport performance analysis and injury prevention: Toward a big data, machine learning future. Journal of Science and Medicine in Sport, 19, e79. doi: 10.1016/j.jsams.2015.12.192

Baraniuk, C. (2015). Rise of the AI sports coach. New Scientist, 227(3035). doi: 10.1016/S0262-4079(15)31025-3

Barshan, B., & Yüksek, M. C. (2014). Recognizing daily and sports activities in two open source machine learning environments using body-worn sensor units. The Computer Journal, 57(11), 1649-1667. doi: 10.1093/comjnl/bxt075

Baumer, B., & Zimbalist, A. (2014). Quantifying Market Inefficiencies in the Baseball Players’ Market. Eastern Economic Journal, 40(4), 488-498. doi: 10.1057/eej.2013.43

Baumer, B. S., Jensen, S. T., & Matthews, G. J. (2015). openWAR: An open source system for evaluating overall player performance in major league baseball. Journal of Quantitative Analysis in Sports, 11(2), 69-84. doi: 10.1515/jqas-2014-0098

Bhandari, I., Colet, E., Parker, J., Pines, Z., Pratap, R., & Ramanujam, K. (1997). Advanced scout: Data mining and knowledge discovery in NBA data. Data Mining and Knowledge Discovery, 1(1), 121-125. doi: 10.1023/A:1009782106822

Bishop, C. (2006). Pattern recognition and machine learning (Springer Ed.). New York.

Bustamante, Á., & Burillo, P. (2016). Gestión y evaluación del rendimiento en baloncesto: una revisión sistemática del software. Retos: nuevas tendencias en educación física, deporte y recreación(29), 72-78.

Courneya, K. S., & Carron, A. V. (1992). The home advantage in sport competitions: A literature review. Journal of Sport and Exercise Psychology, 14(1), 13-27.

Davoodi, E., & Khanteymoori, A. (2010). Horse racing prediction using artificial neural networks. Recent Advances in Neural Networks, Fuzzy Systems & Evolutionary Computing, 55-160.

De Marchi, L. (2011). Data mining of sports performance data. University of Leeds, School of Computing Studies.

Delen, D., Cogdell, D., & Kasap, N. (2012). A comparative analysis of data mining methods in predicting NCAA bowl outcomes. International Journal of Forecasting, 28(2), 543-552. doi: 10.1016/j.ijforecast.2011.05.002

Demens, S. (2015). Riding a probabilistic support vector machine to the Stanley Cup. Journal of Quantitative Analysis in Sports, 11(4), 205-218. doi: 10.1515/jqas-2014-0093

Edelmann-Nusser, J., Hohmann, A., & Henneberg, B. (2002). Modeling and prediction of competitive performance in swimming upon neural networks. European Journal of Sport Science, 2(2), 1-10. doi: 10.1080/17461390200072201

Fister Jr, I., Ljubič, K., Suganthan, P. N., Perc, M., & Fister, I. (2015). Computational intelligence in sports: Challenges and opportunities within a new research domain. Applied Mathematics and Computation, 262, 178-186. doi: 10.1016/j.amc.2015.04.004

Gomez, M. A., Pollard, R., & Luis-Pascual, J. C. (2011). Comparison of the home advantage in nine different professional team sports in Spain 1. Perceptual and motor skills, 113(1), 150-156. doi: 10.2466/05.PMS.113.4.150-156

González-Ruiz, S., Gómez-Gallego, I., Pastrana-Brincones, J., & Hernández-Mendo, A. (2015). Algoritmos de clasificación y redes neuronales en la observación automatizada de registros. Cuadernos de psicología del deporte, 15(1), 31-40.

Hagenbuchner, M., Cliff, D. P., Trost, S. G., Van Tuc, N., & Peoples, G. E. (2015). Prediction of activity type in preschool children using machine learning techniques. Journal of Science and Medicine in Sport, 18(4), 426-431. doi: 10.1016/j.jsams.2014.06.003

Haghighat, M., Rastegari, H., & Nourafza, N. (2013). A review of data mining techniques for result prediction in sports. Advances in Computer Science: an International Journal, 2(5), 7-12.

Hamilton, M., Hoang, P., Layne, L., Murray, J., Padgett, D., Stafford, C., & Tran, H. T. (2014). Applying machine learning techniques to baseball pitch prediction. Paper presented at the Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods.

Hua, K.-L., Lai, C.-T., You, C.-W., & Cheng, W.-H. (2015). An efficient pitch-by-pitch extraction algorithm through multimodal information. Information Sciences, 294, 64-77. doi: 10.1016/j.ins.2014.09.001

Jamieson, J. P. (2010). Home field advantage in athletics: a meta-analysis. Journal of Applied Social Psychology, 819-1848. doi: 10.1111/j.1559-1816.2010.00641.x

Jeff, H., & John, R. (2011). Using Local Correlation to Explain Success in Baseball. Journal of Quantitative Analysis in Sports, 7(4), 1-29. doi: 10.2202/1559-0410.1278

Jelinek, H. F., Kelarev, A., Robinson, D. J., Stranieri, A., & Cornforth, D. J. (2014). Using meta-regression data mining to improve predictions of performance based on heart rate dynamics for Australian football. Applied Soft Computing, 14, 81-87. doi: 10.1016/j.asoc.2013.08.010

Knottenbelt, W. J., Spanias, D., & Madurska, A. M. (2012). A common-opponent stochastic model for predicting the outcome of professional tennis matches. Computers and Mathematics with Applications, 64, 3820-3827. doi: 10.1016/j.camwa.2012.03.005

Link, D., & Lames, M. (2009). Sport Informatics: Historical Roots, Interdisciplinarity and Future Developments. International Journal of Computer Science in Sports, 8(2), 68-87.

Lock, D., & Nettleton, D. (2014). Using random forests to estimate win probability before each play of an NFL game. Journal of Quantitative Analysis in Sports, 10(2), 197-205. doi: 10.1515/jqas-2013-0100

Min, B., Kim, J., Choe, C., Eom, H., & McKay, R. B. (2008). A compound framework for sports results prediction: A football case study. Knowledge-Based Systems, 21(7), 551-562. doi: 10.1016/j.knosys.2008.03.016

Mitchell, T. M. (1997). Machine Learning. New York: McGraw-Hill.

Morgan, S., Williams, M. D., & Barnes, C. (2013). Applying decision tree induction for identification of important attributes in one-versus-one player interactions: A hockey exemplar. Journal of sports sciences, 31(10), 1031-1037. doi: 10.1080/02640414.2013.770906

O'Reilly, N. J., & Knight, P. (2007). Knowledge Management Best Practices in National Sport Organizations. International Journal of Sport Management and Marketing, 2(3), 264-280. doi: 10.1504/IJSMM.2007.012405

Ofoghi, B., Zeleznikow, J., MacMahon, C., & Dwyer, D. (2010). A machine learning approach to predicting winning patterns in track cycling omnium Artificial Intelligence in Theory and Practice III (pp. 67-76): Springer.

Paul, R. J., & Weinbach, A. P. (2009). Sportsbook pricing and the behavioral biases of bettors in the NHL. Journal of Economics and Finance, 36(1), 123-135. doi: 10.1007/s12197-009-9112-4

Piatetsky, S. (2016). Difference between Data Mining and Statistics. http://www.kdnuggets.com/faq/difference-data-mining-statistics.html

Pic, M., & Castellano, J. (2016). Efecto de la localización del partido en eliminatorias de ida y vuelta de la UEFA Champions League. RICYDE. Revista Internacional de Ciencias del Deporte, 44(12), 149-163. doi: 10.5232/ricyde2016.04405

Pollard, R. (1986). Home advantage in soccer: A retrospective analysis. Journal of sports sciences, 4(3), 237-248. doi: 10.1080/02640418608732122

Pollard, R., & Pollard, G. (2005). Long-term trends in home advantage in professional team sports in North America and England (1876–2003). Journal of sports sciences, 23(4), 337-350. doi: 10.1080/02640410400021559

Pueo, B., & Jimenez-Olmedo, J. M. Application of motion capture technology for sport performance analysis (El uso de la tecnología de captura de movimiento para el análisis del rendimiento deportivo). Retos(32), 241-247.

Rama Iyer, S., & Sharda, R. (2009). Prediction of athletes performance using neural networks: An application in cricket team selection. Expert Systems with Applications, 36, 5510-5522. doi: 10.1016/j.eswa.2008.06.088

Sauer, R. D., Waller, J. K., & Hakes, J. K. (2010). The progress of the betting in a baseball game. Public Choice, 142(3-4), 297-313. doi: 10.1007/s11127-009-9544-6

Schumaker, R. P., Solieman, O. K., & Chen, H. (2010). Sports knowledge management and data mining. Annual review of information science and technology, 44(1), 115-157. doi: 10.1002/aris.2010.1440440110

Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding Machine Learning: From Theory to Algorithms: Cambridge University Press.

Shao, S. (2009). Application of BP neural network model in sports aerobics performance In IEEE (Ed.), Knowledge Engineering and Software Engineering, 2009. KESE'09. Pacific-Asia Conference. (pp. 33-35).

Soto-Valero, C. (2017). A Gaussian mixture clustering model for characterizing football players using the EA Sports' FIFA video game system. RICYDE. Revista Internacional de Ciencias del Deporte, 49(13), 244-259. doi: 10.5232/ricyde2017.04904

Soto-Valero, C., & González-Castellanos, M. (2015). Sabermetría y nuevas tendencias en el análisis estadístico del juego de béisbol (Sabermetrics and new trends in statistical analysis of baseball). Retos(28), 122-127.

Soto-Valero, C., Pérez-Morales, I., González-Castellanos, M., & de la Celda Brovkina, A. (2016). ACI-Polo: Sistema computacional para el análisis de la actividad competitiva individual en juegos de polo acuático. Revista Cubana de Ciencias Informáticas, 10(1), 229-244.

Spann, M., & Skiera, B. (2009). Sports forecasting: a comparison of the forecast accuracy of prediction markets, betting odds and tipsters. Journal of Forecasting, 28(1), 55-72. doi: 10.1002/for.1091

Sun, J., Yu, W., & Zhao, H. (2010). Study of association rule mining on technical action of ball Paper presented at the 2010 International Conference on Measuring Technology and Mechatronics Automation.

Van Haaren, J., Ben Shitrit, H., Davis, J., & Fua, P. (2016). Analyzing volleyball match data from the 2014 World Championships using machine learning techniques. Paper presented at the Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.

Witten, I. H., Frank, E., & Hall, M. A. (2011). Data Mining Practical Machine Learning Tools and Techniques (3rd ed.): Morgan Kaufmann Publishers.

Woodland, L. M., & Woodland, B. M. (1994). Market Efficiency and the Favorite-Longshot Bias: The Baseball Betting Market. The Journal of Finance, 49(1), 269-279. doi: 10.1111/j.1540-6261.1994.tb04429.x

Yadav, A., Sharma, A., Gautam, A., Bathla, G., & Jindal, R. (2017). Predicting English Premier League Results using Machine Learning. Computer Engineering & Information Technology, 2017.

Descargas

Archivos adicionales

Publicado

2018-07-01

Cómo citar

Valero, C. S. (2018). Aplicación de métodos de aprendizaje automático en el análisis y la predicción de resultados deportivos (Application of automated learning methods for analyzing and predicting sports outcomes). Retos, 34, 377–382. https://doi.org/10.47197/retos.v0i34.58506

Número

Sección

Experiencias didácticas desarrollas e investigadas con trabajo empírico