Football Analytics using Bayesian Networks: the FutBA Model

Date

2019-01-01

Author

Karabıyık, Mert
Yet, Barbaros

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

353
views

0
downloads

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.

Subject Keywords

Football analytics, Bayesian networks, Predictive models, Futbol analitiği, Bayes ağları, Tahmin modelleri

URI

https://hdl.handle.net/11511/56227

Journal

Pamukkale University Journal of Engineering Sciences

DOI

https://doi.org/10.5505/pajes.2018.12979

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

A Machine Learning Ensembling Approach to Predicting Transfer Values Aydemir, Ayşe Elvan; Taşkaya Temizel, Tuğba; Temizel, Alptekin (2022-03-01) Predicting transfer values of association football players, despite its importance, has been studied in a limited way in the literature. The existing approaches have mainly focused on explanatory models that cannot be used in predicting future values. In this paper, we propose a method where we fuse in-game performance data, player popularity metrics from the web and actual transfer values. The method uses a model ensembling approach to capture diferent dynamics in transfer market. The proposed approach out...
The Computer As A Catalyst For New Educational Paradigms In Architecture Akın, Ömer (Middle East Technical University, Faculty of Architecture, 1995) Günümüzde bilgisayar bir çok meslek dalında kaçınılmaz ve vazgeçilmez bir araç haline gelmiştir. Bilgisayarın bir çok mesleğe getirmiş olduğu büyük yenilik, geleneksel çalışma yöntemlerini aşarak yeni ve verimli çalışma olanaklarını ortaya çıkarmasıdır. Mimarlık ve mimarlık eğitiminde de bu gelişme er ya da geç oluşacaktır. Tarihsel bir çerçeve içinde ele alınırsa, mimarlık son beşyüz yıl içinde iki büyük aşamadan geçmiştir. Bu aşamalar, Ecoles de Beaux Arts ve Bauhaus gibi eğitim sistemlerinin kalıplaştırd...
GTD solution with higher order terms to the diffraction by an edge: Towards a uniform solution Buyukdura, OM (Institution of Engineering and Technology (IET), 1996-02-01) A UTD solution for an edge of a perfectly conducting wedge is presented which includes terms of order higher than the ordinary UTD. The problem is studied for three special cases: (i) plane and (ii) spherical wave incidence on a straight wedge with planar surfaces, and (iii) cylindrical wave incidence on a wedge with surfaces curved in the direction normal to the edge. This solution not only compensates the jump discontinuities in the GO field but also the discontinuities in the derivative. The solution fou...
Migrants ‘at home’ or ‘visiting’?: Insights on the collective identities of the Turkish diaspora football supporters Alpan, Başak Zeynep (null; 2018-06-15) If there is one thing that academia has learnt from football, it is that football indeed emerged as a significant marker of identity. Football, due to its fundamental design of binary oppositions, continuously invites the spectator – even if his/her ‘own’ team is not involved – to take sides and express partisanship. The picture gets even more complicated when the inter-related processes of migration and diasporic identification on the part of fan identities shape and respond to collective and spatial polit...
Marketing strategies: two case studies of Real Madrid football club and Fenerbahçe sports club Altun Ekinci, Merve; Koçak, Mehmet Settar; Department of Physical Education and Sports (2018) Within their dominant positions, Real Madrid Football Club (CF) and Fenerbahçe Sports Club (SC) present valuable examples for understanding the underlying factors of how two clubs differently develop value creating strategies to gain asporting and commercial position in the competitive scope of the football business. This study intends to analyze and compare the marketing strategies of Real Madrid CF & Fenerbahçe SC within the scope of Dolles & Söderman (2013a)‘s network of value captures research framework...

Citation Formats

M. Karabıyık and B. Yet, “Football Analytics using Bayesian Networks: the FutBA Model,” Pamukkale University Journal of Engineering Sciences, pp. 121–131, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/56227.