{"title":"Predict soccer match outcome based on player performance","authors":"Wei Yang","doi":"10.25236/FSR.2021.030314","DOIUrl":null,"url":null,"abstract":"In the field of sports, due to the unpredictability of soccer match outcome and the existence of sports betting industry, the prediction of soccer match results has been highly concerned by the news media, fans, sports experts and other stakeholders, and it is also a hot topic in academic circles. The strength of the team is made up of players. Player performance is a key factor in winning a soccer match. This article builds a model to predict the outcome of the match based on the performance of the players. In experiments, the statistics of the AUC, F1 and prediction accuracy of the model were 0.8597, 0.6973 and 0.7965 respectively on the verification data. The experimental results also show the feasibility of this method.","PeriodicalId":326635,"journal":{"name":"Frontiers in Sport Research","volume":"31 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Sport Research","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25236/FSR.2021.030314","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In the field of sports, due to the unpredictability of soccer match outcome and the existence of sports betting industry, the prediction of soccer match results has been highly concerned by the news media, fans, sports experts and other stakeholders, and it is also a hot topic in academic circles. The strength of the team is made up of players. Player performance is a key factor in winning a soccer match. This article builds a model to predict the outcome of the match based on the performance of the players. In experiments, the statistics of the AUC, F1 and prediction accuracy of the model were 0.8597, 0.6973 and 0.7965 respectively on the verification data. The experimental results also show the feasibility of this method.