A novel hybrid ensemble model based on tree-based method and deep learning method for default prediction

作者：

Highlights：

• A novel hybrid ensemble model for default prediction is proposed.

• LightGBM is used to build new feature interactions to enhance feature expression.

• CNN is used to build new feature interactions to reflect deeper information.

• Ensemble model combining deep learning and tree-based classifiers are used.

• The proposed model outperforms comparative methods in four evaluation metrics.

摘要

•A novel hybrid ensemble model for default prediction is proposed.•LightGBM is used to build new feature interactions to enhance feature expression.•CNN is used to build new feature interactions to reflect deeper information.•Ensemble model combining deep learning and tree-based classifiers are used.•The proposed model outperforms comparative methods in four evaluation metrics.

论文关键词：Feature generation,Deep learning,Ensemble learning,Default prediction,Binary classification

论文评审过程：Received 12 November 2019, Revised 14 January 2021, Accepted 6 March 2021, Available online 13 March 2021, Version of Record 25 March 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.114899