A novel method for prediction of EuroLeague game results using hybrid feature extraction and machine learning techniques

Serkan Ballı and Engin Özdemir

Chaos, Solitons & Fractals, 2021, vol. 150, issue C

Abstract: Basketball competitions are among the most watched sports activities in the world. With the developing technology, statistics of the games and players of basketball can be stored more easily, so artificial intelligence techniques such as machine learning can be used for decision making and prediction. While there are studies on American leagues and especially the NBA on the predictions of the results of basketball competitions, the number of studies on European leagues in this regard is insufficient. In this study, for the first time in the literature, EuroLeague matches have been evaluated with the hybrid of Four Factors and DefenseOfense models together and then machine learning methods have been applied for the prediction of game results. Accordingly, the matches played between the seasons of 2012–2013 and 2016–2017 have been used as 5 different data sets. New features have been extracted using with Four Factors and DefenseOfense models together and 8 different feature models have been obtained. Then, machine learning methods such as kNN, Logistic Regression, Multilayer Perceptron, Naive Bayes, j48 and Voting have been used and the results have been discussed. Finally, 98.90% prediction success has been achieved with the Multilayer Perceptron method by using Dataset 5 and Model 6.

Keywords: Multilayer perceptron; EuroLeague; Four factors; Machine learning; Prediction; Sport science (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960077921004732
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:chsofr:v:150:y:2021:i:c:s0960077921004732

DOI: 10.1016/j.chaos.2021.111119

Access Statistics for this article

Chaos, Solitons & Fractals is currently edited by Stefano Boccaletti and Stelios Bekiros

More articles in Chaos, Solitons & Fractals from Elsevier
Bibliographic data for series maintained by Thayer, Thomas R. ().