A comparative study on base classifiers in ensemble methods for credit scoring

详细信息    查看全文

• 作者：Joaquí ; n Abellá ; n ; ^{jabellan@decsai.ugr.es} ; Javier G. Castellano ^{fjgc@decsai.ugr.es}
• 关键词：Credit scoring ; Ensembles of classifiers ; Base classifier ; Decision trees ; Imprecise Dirichlet model ; Uncertainty measures
• 刊名：Expert Systems with Applications
• 出版年：2017
• 出版时间：1 May 2017
• 年：2017
• 卷：73
• 期：Complete
• 页码：1-10
• 全文大小：1207 K
• 卷排序：73

文摘

Small improvements in the systems about credit scoring can suppose great profits. Ensembles of classifiers achieve the better results for credit risk assessment. To look for the best base classifier used in ensembles on credit datasets is an important task. Via experiments, it is shown that the credal decision tree classifier is the best one to be used in ensembles. The study uses several of the most successful ensemble schemes and single classifiers.