A novel dynamic ensemble selection classifier for an imbalanced data set: An application for credit risk assessment
作者:
Highlights:
• A novel DES model for imbalanced data set is proposed for credit scoring.
• The synthetic minority over-sampling technique is used to balance the training set.
• The meta-training process of META-DES is used to evaluate classifiers competence.
• The instances in competent region are weighted to enhance minority influence.
• The strategy of DESKNN is used to trade off classifiers’ competence and diversity.
摘要
•A novel DES model for imbalanced data set is proposed for credit scoring.•The synthetic minority over-sampling technique is used to balance the training set.•The meta-training process of META-DES is used to evaluate classifiers competence.•The instances in competent region are weighted to enhance minority influence.•The strategy of DESKNN is used to trade off classifiers’ competence and diversity.
论文关键词:Credit risk assessment,Dynamic ensemble selection (DES),Imbalanced classification,Resampling techniques
论文评审过程:Received 28 May 2020, Revised 30 July 2020, Accepted 3 September 2020, Available online 16 September 2020, Version of Record 19 September 2020.
论文官网地址:https://doi.org/10.1016/j.knosys.2020.106462