The Effect of Weather in Soccer Results: An Approach Using Machine Learning Techniques
View/ Open
Impact
Scholar |
Other documents of the author: Iskandaryan, Ditsuhi; Ramos, Jose Francisco; Palinggi, Denny Asarias; Trilles, Sergio
Metadata
Show full item recordcomunitat-uji-handle:10234/9
comunitat-uji-handle2:10234/43662
comunitat-uji-handle3:10234/43643
comunitat-uji-handle4:
INVESTIGACIONMetadata
Title
The Effect of Weather in Soccer Results: An Approach Using Machine Learning TechniquesDate
2020-09-26Publisher
MDPIISSN
2076-3417Bibliographic citation
IIskandaryan, D.; Ramos, F.; Palinggi, D.A.; Trilles, S. The Effect of Weather in Soccer Results: An Approach Using Machine Learning Techniques. Appl. Sci. 2020, 10, 6750Type
info:eu-repo/semantics/articlePublisher version
https://www.mdpi.com/2076-3417/10/19/6750/htmVersion
info:eu-repo/semantics/publishedVersionSubject
Abstract
The growing popularity of soccer has led to the prediction of match results becoming of interest to the research community. The aim of this research is to detect the effects of weather on the result of matches by ... [+]
The growing popularity of soccer has led to the prediction of match results becoming of interest to the research community. The aim of this research is to detect the effects of weather on the result of matches by implementing Random Forest, Support Vector Machine, K-Nearest Neighbors Algorithm, and Extremely Randomized Trees Classifier. The analysis was executed using the Spanish La Liga and Segunda division from the seasons 2013–2014 to 2017–2018 in combination with weather data. Two tasks were proposed as part of this study: the first was to find out whether the game will end in a draw, a win by the hosts or a victory by the guests, and the second was to determine whether the match will end in a draw or if one of the teams will win. The results show that, for the first task, Extremely Randomized Trees Classifier is a better method, with an accuracy of 65.9%, and, for the second task, Support Vector Machine yielded better results with an accuracy of 79.3%. Moreover, it is possible to predict whether the game will end in a draw or not with 0.85 AUC-ROC. Additionally, for comparative purposes, the analysis was also performed without weather data. [-]
Is part of
Applied Sciences, 2020, vol. 10, no 19Investigation project
Universitat Jaume I: PREDOC/2018/61; Ministry of Science and Innovation-Spanish government: IJC2018-035017-I; Generalitat Valenciana: GV/2020/035Rights
info:eu-repo/semantics/openAccess
This item appears in the folowing collection(s)
- INIT_Articles [754]
The following license files are associated with this item: