Improving logistic regression classification of credit approval with features constructed by kaizen programming
Data
2016
Autores
de Melo, Vinicius Veloso 
Tipo
Trabalho apresentado em evento
Título da Revista
ISSN da Revista
Título de Volume
Resumo
In this contribution, we employ the recently proposed Kaizen Programming (KP) approach to fi nd high-quality nonlinear combinations of the original features in a dataset. KP constructs many complementary features at the same time, which are selected by their importance, not by model quality. We investigated our approach in a well-known realworld credit scoring dataset. When compared to related approaches, KP reaches similar or better results, but evaluates fewer models.
Descrição
Citação
Proceedings Of The 2016 Genetic And Evolutionary Computation Conference (GECCO'16 Companion). New york, p. 61-62, 2016.