Bayes ağları ile futbol analitiği: FutBA modeli

Öz

Futbol maçları yüksek belirsizliğe sahiptir ve sonuçlarının tahmin edilmesi zordur. Sadece veriye dayalı tahmin ve yapay öğrenme yöntemleri futbol tahminlerinde kısıtlı performans elde edebilmektedir. Uzman bilgisine dayalı modeller başarıya sahip olmuştur, fakat bu modellerin başka yerlere uygulanması için yine uzman bilgisi ve analistler tarafından gözden geçirilmesi gerekmektedir. Bu çalışmada Türkiye futbol ligleri için geliştirilmiş özgün bir Bayes ağı modeli önerilmektedir. Önerilen model futbol müsabakası yapan takımların hücum ve savunma gücünü maça ilişkin birçok gözlem ile belirleyerek maç sonucunu tahmin etmeyi amaçlamaktadır. Modelin yapısı ve parametreleri uzman bilgisi ile geliştirilmiştir. Modelden tahmin üretirken geçmiş maç verisi ile maça ilişkin uzman bilgisi girdi olarak kullanılabilmektedir. Önerilen model Türkiye Süper Ligi’nden gerçek maç verisi ile değerlendirilmiştir.

Anahtar Kelimeler

• Futbol analitiği,Bayes ağları,Tahmin modelleri

Football analytics using Bayesian networks: The FutBA model

Abstract

The results of football matches are difficult to predict due to their high uncertainty. Previous applications of data-driven machine learning approaches had limited performance in this prediction problem. Models that use expert knowledge had relatively higher performance but it is difficult to adapt these models to different cases as they need to be reviewed by experts and analysts based on specific requirements of the new application. This paper proposes a novel Bayesian network model to predict the results of football matches in Turkish football leagues. The Bayesian network model predicts the match results by estimating the attack and defense capability of the teams based on multiple observations about the football match. The structure and parameters of the model is defined based on expert knowledge. The model is able to use statistical data from previous matches and expert knowledge about these factors to generate predictions. The proposed model is evaluated by using data from the Turkish Super League.

Keywords

• Football analytics,Bayesian networks,Predictive models

References

1. Constantinou AC, Fenton NE, Neil M. "Pi-football: A Bayesian network model for forecasting association football match outcomes". Knowledge-Based Systems 36, 322-339, 2012.
2. Dixon MJ, Coles SG. "Modelling association football scores and ınefficiencies in the football betting market". Journal of the Royal Statistical Society: Series C (Applied Statistics) 46(2), 265-280, 1997.
3. Crowder M, Dixon M, Ledford A, Robinson M. "Dynamic modelling and prediction of English football league matches for betting". Journal of the Royal Statistical Society: Series D (The Statistician), 51(2), 157-168, 2002.
4. Joseph A, Fenton NE, Neil M. "Predicting football results using Bayesian nets and other machine learning techniques". Knowledge-Based Systems, 19(7), 544-553, 2006.
5. Rotshtein AP, Posner M, Rakityanskaya AB. "Football predictions based on a fuzzy model with genetic and neural tuning". Cybernetics and Systems Analysis, 41(4), 619-630, 2005.
6. Karaoğlu B. "Makine öğrenmesi ile spor karşılaşmalarının modellenmesi modelling sports games using machine learning". Emobilimsel Dergi, 5(9), 1-5, 2015.
7. Hucaljuk J, Rakipovic A. "Predicting football scores using machine learning techniques". 34th International Convention MIPRO, Opatija, Croatia, 23-27 May 2011.
8. Fenton NE, Neil M. Risk Assessment and Decision Analysis With Bayesian Networks. Boca Raton, FL, CRC Press, 2012.

9. Lauritzen SL, Spiegelhalter D. "Local computations with probabilities on graphical structures and their application to expert systems". Journal of the Royal Statistical Society Series B (Methodological) 50(2), 157-224, 1988.
10. Constantinou A, Fenton N. "Towards smart-data: Improving predictive accuracy in long-term football team performance". Knowledge-Based Systems 124, 93-104, 2017.
11. Constantinou AC, Fenton NE, Hunter Pollock LJ. "Bayesian networks for unbiased assessment of referee bias in Association Football". Psychology of Sport and Exercise 15(5), 538-547, 2014.
12. Pearl J. Probabilistic Reasoning in Intelligent Systems: Networks of plausible inference. San Mateo, CA, Morgan Kaufmann,1988.
13. Agena. "AgenaRisk: Bayesian Network and Simulation Software for Risk Analysis and Decision Support". http://www.agenarisk.com/ (18.01.2018).
14. Bayesfusion. "GeNIe Modeler". https://www.bayesfusion.com/genie-modeler (18.01.2018).
15. Norsys. "Netica Application". http://www.norsys.com/netica.html (18.01.2018).
16. Van der Gaag LC, Renooij S, Witteman C, Aleman BMP, Taal BG. "How to elicit many probabilities". 15th Conference on Uncertainty in Artificial Intelligence, Stockholm, Sweden, 30 July-01 August 1999.
17. Renooij S. "Probability elicitation for belief networks: Issues to consider". Knowledge Engineering Review, 16(3), 255-269, 2001.
18. Fenton NE, Neil M, Caballero JG. "Using ranked nodes to model qualitative judgments in Bayesian networks". IEEE Transactions on Knowledge and Data Engineering, 19(10), 1420-1432, 2007.
19. Hubbard D. How to measure anything: Finding the value of intangibles in business. Hoboken, NJ, John Wiley & Sons, 2014.
20. Çinicioğlu EN, Atalay M, Yorulmaz H. "Trafik kazaları analizi için bayes ağları modeli". Bilişim Teknolojileri Dergisi, 6(2), 41-52, 2013.
21. Okutan A, Yildiz OT. "Software defect prediction using Bayesian networks". Empirical Software Engineering, 19(1), 154-181, 2014.
22. Lee E, Park Y, Shin JG. "Large engineering project risk management using a Bayesian belief network". Expert Systems with Applications, 36(3), 5880-5887, 2009.
23. Cobb BR, Shenoy PP, Neil M, Tailor M, Marquez D. "Inference in hybrid Bayesian networks with mixtures of truncated exponentials". International Journal of Approximate Reasoning 41(3), 257-286, 2006.
24. Neil M, Tailor M, Marquez D. "Inference in hybrid Bayesian networks using dynamic discretization". Statistics and Computing, 17(3), 219-233, 2007.
25. Yet B, Perkins Z, Fenton N, Tai N, Marsh W. "Not just data: A method for improving prediction with knowledge". Journal of Biomedical Informatics 48, 28-37, 2014.
26. Maher MJ. "Modelling association football scores". Statistica Neerlandica, 36(3), 109-118, 1982.
27. Karlis D, Ntzoufras L. "Analysis of sports data by using bivariate Poisson models". Journal of the Royal Statistical Society Series D: The Statistician, 52(3), 381-393, 2003.
28. Rue H, Salvesen Ø. "Prediction and Retrospective Analysis of Soccer Matches in a League ". Journal of the Royal Statistical Society: Series D (The Statistician), 49(3), 399-418, 2000.
29. Baio G, Blangiardo M. "Bayesian hierarchical model for the prediction of football results". Journal of Applied Statistics, 37(2), 253-64, 2010.
30. Jensen F V., Madsen AL. Bayesian Networks and Decision Graphs. New York, USA, Springer, 2007.
31. Liu HY, Hopkins W, Gomez MA, Molinuevo JS. "Inter-operator reliability of live football match statistics from OPTA sportsdata". International Journal of Performance Analysis in Sport, 13(3), 803-821, 2013.