Research on soccer prediction model based on machine learning combined with domain knowledge

Junxian Song

doi:10.54254/2755-2721/21/20231136

Research Article

Open access

Published on 23 October 2023

Download pdf

Song,J. (2023). Research on soccer prediction model based on machine learning combined with domain knowledge. Applied and Computational Engineering,21,161-168.

Export citation

Research on soccer prediction model based on machine learning combined with domain knowledge

Junxian Song *^,1,

¹ Harbin Institute of Technology

* Author to whom correspondence should be addressed.

https://doi.org/10.54254/2755-2721/21/20231136

Abstract

With the global popularity of soccer and the increasing collection of data, more and more research focuses on using machine learning (ML) algorithms to predict match outcomes. However, accurately predicting soccer match results is a complex task that requires considering multiple factors such as team strength and player status. This paper aims to predict soccer match results using ML techniques in Python. To achieve this goal, a series of methods are employed to collect, analyze, and utilize historical match data, combined with knowledge and experience from the soccer domain, to identify factors relevant to predicting soccer match outcomes. By establishing appropriate feature extraction and selection methods, this paper is able to capture information closely related to match results. Based on this foundation, the paper proceeds with model development and enhances its performance through training and parameter tuning. Specifically, ML algorithms such as Support Vector Machines (SVM) and various techniques are applied to optimize the models and improve their predictive accuracy. Emphasis is placed on model stability and generalization, taking into account issues of overfitting and underfitting during the training process, with appropriate regularization and cross-validation techniques. Finally, a comprehensive performance evaluation is conducted on the established models, and a comparative analysis of different algorithms is performed. The experimental results demonstrate the excellent performance of the models proposed in this paper in predicting soccer match results, showcasing the significant potential of ML in this domain.

Keywords

machine learning, domain knowledge, extreme gradient boosting, support vector machines, performance evaluation

View pdf

References

[1]. C.Reep and B.Benjamin, “Skill and Chance in Association Football”, Journal of the Royal Statistical Society, vol 131 , pp 581-585, 1968.

[2]. M.J.Maher, “Modelling association football scores”, Statistica Neerlandica, vol 36, pp 109-118,1982.

[3]. H.Rue S.Martino and N.Chopin, “Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations”, Journal of the Royal Statistical Society: Series B (Statistical Methodology), vol 71(2), pp 319-392, 2009.

[4]. P.Promvijittrakarn and T.Charoenpong, “A method of soccer-team identification by histogram feature vector and support vector machine”, International Workshop on Advanced Imaging Technology, vol 12592, p 12, 2023.

[5]. M.Şahin and R.Erol, “A Comparative Study of Neural Networks and ANFIS for Forecasting Attendance Rate of Soccer Games”, Mathematical and Computational Applications, vol 22, p 43, 2017.

[6]. A.Decuyper A.Troncoso and D.Martens, “Forecasting Association Football Match Outcomes in a Simulated Environment: A Neural Network Approach”, Journal of Sports Analytics, vol 5(2), pp 85-96, 2019.

[7]. Bloomfield Polman and O’Donoghue, “The ‘Bloomfield Movement Classification’: Motion Analysis of Individual Players in Dynamic Movement Sports”, International Journal of Performance Analysis in Sport, vol 4, pp 20-31, 2004.

[8]. M.J.Dixon and S.G.Coles, “Modelling Association Football Scores and Inefficiencies in the Football Betting Market”, Journal of the Royal Statistical Society , vol 46(2), pp 265-280, 1997.

[9]. O.Hubáček G.Šourek and F.Železný, “Learning to predict soccer results from relational data with gradient boosted trees”, Springer, vol 108, pp 29-47, 2019.

[10]. D.Berrar P.Lopes and W.Dubitzky, “Incorporating domain knowledge in machine learning for soccer outcome prediction”, Springer, vol 108, pp 97-126, 2019.

[11]. Y.Cho J.Yoon and S.Lee, “Using social network analysis and gradient boosting to develop a soccer win–lose prediction model”, Engineering Applications of Artificial Intelligence, vol 72 pp 228-240,2018.

[12]. H. Rue and Øyvind Salvesen, “Focus on Sport: Prediction and Retrospective Analysis of Soccer Matches in a League”, Journal of the Royal Statistical Society, vol 49, pp 399-418, 2000.

[13]. D.Berrar P. Lopes J.Davis and W.Dubitzky, “Guest editorial: special issue on machine learning for soccer”, Springer, vol 108, pp 1-7, 2019.

Cite this article

Song,J. (2023). Research on soccer prediction model based on machine learning combined with domain knowledge. Applied and Computational Engineering,21,161-168.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About volume

Volume title: Proceedings of the 5th International Conference on Computing and Data Science

Conference website: https://2023.confcds.org/

ISBN：978-1-83558-033-2(Print) / 978-1-83558-034-9(Online)

Conference date: 14 July 2023

Editor：Roman Bauer, Alan Wang, Marwan Omar

Series: Applied and Computational Engineering

Volume number: Vol.21

ISSN：2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).