Evaluating the effect of voting methods on ensemble-based classification

Abstract

Bagging is a popular method used to increase the accuracy of classification, by training a set of classifiers on slightly different datasets and aggregating their output by voting. Usually, the majority voting is used for this purpose, or the plurality voting, when the problem has multiple class values. In this study, we analyze the influence of several voting methods on the performance of two classification algorithms used for datasets with different levels of difficulty. The results reveal that the single transferable vote can be a good alternative to plurality voting, although it has the drawback of a higher computational cost related to the calculation of preference ordering.