A hybrid scheme-based one-vs-all decision trees for multi-class classification tasks

作者：

Highlights：

• This is the first paper to deal with the class imbalanced problem caused by OVA strategy.

• A novel split criterion is proposed to tackle the imbalanced problem caused by OVA strategy.

• The proposed method selects the optimal splitting point from multi-angle.

• The proposed method significantly reduces the depth of decision tree.

摘要

•This is the first paper to deal with the class imbalanced problem caused by OVA strategy.•A novel split criterion is proposed to tackle the imbalanced problem caused by OVA strategy.•The proposed method selects the optimal splitting point from multi-angle.•The proposed method significantly reduces the depth of decision tree.

论文关键词：Decision tree,One-vs-all,Split criteria,Hybrid scheme,Multi-class classification

论文评审过程：Received 27 June 2019, Revised 30 March 2020, Accepted 14 April 2020, Available online 20 April 2020, Version of Record 22 April 2020.

论文官网地址：https://doi.org/10.1016/j.knosys.2020.105922