A Bayesian approach for major European football league match prediction

Document Type : Research Paper


1 Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Malaysia

2 Faculty of Applied Sciences and Technology, Universiti Tun Hussein Onn Malaysia, Malaysia

3 Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Malaysia

4 School of Sport and Leisure, Viana do Castelo Polytechnic Institute, Portugal


This paper presents a Bayesian Approach for Major European Football League match prediction. In this study, four variants of Bayesian approaches are investigated to observe the impact of different structural learning algorithms within the family of Bayesian Network which are Naive Bayes (NB), Tree Augmented Naive Bayes (TAN) and two General Bayesian Networks (GBN); K2 algorithm with BDeu scoring function (GBN-K2) and Hill Climbing algorithm with MDL scoring function (GBNHC). The predictive performance of all Bayesian approaches is evaluated and compared based on football match results from five major European Football League consisting of three complete seasons of 1,140 matches. The results showed that GBN-HC gained 92.01% of accuracy while GBN-K2 and TAN produced comparable results with 91.86% and 91.94% accuracy, respectively. The lowest result was produced by NB, with only 72.78% accuracy. The results suggest that TAN requires further exploration in football prediction with its ability to cater the minimal dependency among attributes in a small-sized dataset.


[1] S. L. Ang, H. C. Ong, and H. C. Low, Classification Using the General Bayesian Network,” Pertanika J. Sci.
Technol., 24 (1) (2016) 205–211.
[2] G. Baio and M. Blangiardo, Bayesian hierarchical model for the prediction of football results, J. Appl. Stat.,
(2010) 1–13.[3] G. Bielza and P. Larra˜naga, Discrete bayesian network classifiers: A survey, ACM Comput. Surv., 47 (1) (2014).
[4] W. Buntine, Theory refinement on Bayesian networks, Proc. Seventh Annu. Conf. Uncertain. Artif. Intell., (1991)
[5] A. C. Constantinou, N. E. Fenton, and M. Neil, Knowledge-Based Systems Profiting from an inefficient association
football gambling market: Prediction , risk and uncertainty using Bayesian networks, Knowledge-Based Syst., 50
(2013) 60–86.
[6] A. C. Constantinou, N. E. Fenton, and M. Neil, Pi-football: A Bayesian network model for forecasting Association
Football match outcomes, Knowledge-Based Syst., 36 (2012) 322–339.
[7] A. C. Constantinou, Dolores: a model that predicts football match outcomes from all over the world, Mach. Learn.,
(2019) 1–27.
[8] G. F. Cooper and E. Herskovits, A Bayesian method for the induction of probabilistic networks from data, Mach.
Learn., 9 (1992) 309–347.
[9] W. Dubitzky, P. Lopes, J. Davis, and D. Berrar, “The Open International Soccer Database for machine learning,”
Mach. Learn., 108 (1) (2019) 9–28.
[10] J. Fernandez, D. Medina, M. A. Gomez, and R. Gavalda, From training to match performance: A predictive and
explanatory study on novel tracking data, IEEE Int. Conf. Data Min. Work., ( 2017) 136–143.
[11] E. Frank, M. A. Hall, and I. H. Witten, The WEKA Workbench. Online Appendix for Data Mining: Practical
Machine Learning Tools and Techniques, Morgan Kaufmann, Fourth Ed., (2016).
[12] N. Friedman, M. Geiger, and M. Goldszmidt, Bayesian network classifier, Mach. Learn., 29 (2) (1997) 131–163.
[13] D. Geiger, An entropy-based learning algorithm of Bayesian conditional trees, Proc. Eighth Annu. Conf. Uncertain.
Artif. Intell., (1992) 92–97.
[14] D. Heckerman, D. Geiger, and D. M. Chickering, Learning Bayesian Networks: The Combination of Knowledge
and Statistical Data, Mach. Learn., 20 (3) (1995) 197–243.
[15] J. Heaton, Quantifying the performance of individual players in a team activity, Forecast. Futur., 7 (2013) 6–10.
[16] D. E. Holmes and L. C. (eds) Jain, Innovations in Bayesian Networks: Theory and Applications, Stud. Comput.
Intell. Springer, 156 (2008).
[17] J. Ji, C. Yang, J. Liu, J. Liu, and B. Yin, A comparative study on swarm intelligence for structure learning of
Bayesian networks, Soft Comput., 21 (22)(2017) 6713–6738.
[18] G. H. John and L. P., Estimating Continuous Distributions in Bayesian Classifiers, Elev. Conf. Uncertain. Artif.
Intell., (1995) 338–345.
[19] A. Joseph, N. E. Fenton, and M. Neil, Predicting football results using Bayesian nets and other machine learning
techniques, Knowledge-Based Syst., 19 (7) (2006) 544–553.
[20] A. S. Hesar, T. H., and M. Jalali, Structure Learning of Bayesian Networks Using Heuristic Methods, Pertanika
J. Sci. Technol., 45 (2012) 246–250.
[21] M. G. Madden, On the classification performance of TAN and General Bayesian Networks, Knowledge-Based
Syst., 22 (2) (2009) 295–489.
[22] B. Min, J. Kim, C. Choe, H. Eom, and R. I. (Bob) McKay, A compound framework for sports results prediction:
A football case study, Knowledge-Based Syst., 21 (7) (2008) 551–562, 2008.
[23] A. Owen, Dynamic Bayesian forecasting models of football match outcomes with estimation of the evolution
variance parameter, IMA J. Manag. Math., 22 (2) pp. 99–113, 2011.
[24] F. Owramipur, P. Eskandarian, and F. S. Mozneb, “Football Result Prediction with Bayesian Network in Spanish
League-Barcelona Team,” Int. J. Comput. Theory Eng., 5 (5) (2013) 812–815.
[25] J. Pearl, Bayesian Networks: A Model of Self-Activated Memory for Evidential Reasoning, Rep. No CSD-850021,
[26] N. Razali, A. Mustapha, S. Utama, and R. Din, A Review on Football Match Outcome Prediction using Bayesian
Networks, J. Phys. Conf. Ser., 1020 (1) (2018).
[27] S. Singhal and M. Jena, A study on WEKA tool for data preprocessing, classification and clustering, Int. J. Innov.
Technol. Explor. Eng., 2 (6) (2013) 250–253.
[28] P. Tufekci, Prediction of football match results in Turkish super league games, IEEE Int. Conf. Data Min. Work.,
427 (2016) 515–526.
Volume 12, Special Issue
December 2021
Pages 971-980
  • Receive Date: 01 June 2021
  • Revise Date: 10 September 2021
  • Accept Date: 24 September 2021