A two-stage hybrid credit risk prediction model based on XGBoost and graph-based deep neural network

作者：

Highlights：

• We propose a new two-stage hybrid model for credit risk prediction task.

• We provide to transform the initial feature set by using XGBoost method.

• We provide to investigate the feature graph with XGBoost method.

• We apply graph-based deep neural network for the credit risk prediction.

• The proposed model achieves prediction performance with superiority.

摘要

•We propose a new two-stage hybrid model for credit risk prediction task.•We provide to transform the initial feature set by using XGBoost method.•We provide to investigate the feature graph with XGBoost method.•We apply graph-based deep neural network for the credit risk prediction.•The proposed model achieves prediction performance with superiority.

论文关键词：Feature engineering,Graph-based deep neural network,Hybrid model,XGBoost,Credit risk prediction

论文评审过程：Received 15 April 2021, Revised 28 August 2021, Accepted 27 January 2022, Available online 1 February 2022, Version of Record 18 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116624