Many statistical models are widely used to predict the result of a soccer match; the standard predictive criterium of classification is the the majority rule, which corresponds to the mode in a polytomous case. In this study, other predictive criteria are proposed and compared with the modal one. The predictive performances are evaluated considering a set of indicators built from the resulting 3x3 confusion matrix. The data used come from the Kaggle European Soccer Database and refer to the seasons from 2009/2010 to 2015/2016 of the Italian League Serie A.
On classifiers to predict soccer match results
Silvia Golia
;Maurizio Carpita
2018-01-01
Abstract
Many statistical models are widely used to predict the result of a soccer match; the standard predictive criterium of classification is the the majority rule, which corresponds to the mode in a polytomous case. In this study, other predictive criteria are proposed and compared with the modal one. The predictive performances are evaluated considering a set of indicators built from the resulting 3x3 confusion matrix. The data used come from the Kaggle European Soccer Database and refer to the seasons from 2009/2010 to 2015/2016 of the Italian League Serie A.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
