Forecasting Football Matches: An Analysis on Predictive Models and Performance Evaluation Techniques for Betting
Keywords:
Data Mining, Sports Betting, Feature Selection, Distribution, FootballAbstract
Football is one of the foremost widely followed sports in the world, thus
fans, coaches, the media, gamblers are all interested in understanding
the game and forecasting the results. It is impossible to predict the
result of a football match, yet the football industry has expanded all
through time. The un predictable nature of football games, as well as
the expansion of the betting industry, point to the creation of predictive
models to assist punters. In this work, we create a machine learning
approach for predicting the outcome of a football match using a
collection of data from past matches and the attributes of the players
on both sides. Several hypotheses were investigated, the experimental
findings demonstrated that performance in the setting of competitive
football is supported by data.
References
Soccer Vista Football Results, Predictions and Betting Options, 2018. Available from: http://www.soccervista. com. Last visited: January 10, 2022.
Forebet, football numbers, tips, stats, preview, 2018. Available from: https://www.forebet.com. Last accessed: January 10, 2022.
Bojanova I. IT enhances football at world cup 2014. IT Specialist 2014; 16(4): 12-7. [Google Scholar]
Gomes J, Portela P, Santos MF. Decision support to predict the outcome of a football match. 2015, pp. 348-353. [Google Scholar]
Ruiz H, Hwj Chim P, Wei X, et al. Leicester City tales? Comparing the performance of the 15/16 and 16/17 EPL seasons using new football analysis tools. In the Proceedings of the 23rd ACM SIGKDD International Conference on Information Discovery and Data Mining,
, p. 1991-2000.
Cañizares PC, Merayo MG, Nunez M, Suarez-Paniagua V.A multi-agent system architecture for statistics managing and soccer forecasting. IEEE International Conference on Computational Intelligence and Applications (ICCIA), p. 107-111, 572-576. [Google
Scholar]
Prasetio, D., 2016, August. Predicting football match results with logistic regression. In 2016 International Conference on Advanced Informatics: Concepts, Theory and Application (ICAICTA), pp. 1-5. [Google Scholar]
Zuccolotto P, Carpita M, Sandri M, et al. Football mining with R. In using Data Mining with R. 2014.
Stübinger J, Mangold B, Knoll J. Education in football: gambling results based on player traits. Applied Sciences 2020; 10(1): 46. [Google Scholar]
Dasgupta, N., 2018. Practical big data analytics: Handson techniques to implement enterprise analytics and machine learning using Hadoop, Spark, NoSQL and R. Packt Publishing Ltd. [Google Scholar]
Kürsa MB, Rudnicki W., Use Boruta button for special options. J Stat Software 2010; 36(11): 1-13.
