A novel self-adaptive differential evolution for feature selection using threshold mechanism
Dušan Fister, Iztok Fister, Timotej Jagrič, Iztok Fister, Janez Brest · 2018
Nowadays, most of databases for classification or regression consists of numerous features that describe the domain of interest. Therefore, they may have a huge influence on the results of classification/regression. A lot of research has shown that some features can be eliminated before the classification/regression in order to obtain better results. In this paper, we propose a novel solution that is based on self-adaptive differential evolution for feature selection on a econometric database. A new solution is systematically presented in this paper. Results of the proposed feature selection method, according to the ROC-AUC score, overcome results, obtained without using it.