Utilizing historical data for corporate credit rating assessment

作者：

Highlights：

• Utilizing historical data can improve the prediction accuracy of credit rating.

• New metrics that can be applied to any artificial intelligence methods are built.

• A new ensemble structure of artificial neural networks is developed.

• Real-world data were used to validate our proposed model for credit rating assessment.

摘要

•Utilizing historical data can improve the prediction accuracy of credit rating.•New metrics that can be applied to any artificial intelligence methods are built.•A new ensemble structure of artificial neural networks is developed.•Real-world data were used to validate our proposed model for credit rating assessment.

论文关键词：Credit rating,Ensemble learning,Artificial Neural Networks,Artificial Intelligence

论文评审过程：Received 28 January 2020, Revised 25 August 2020, Accepted 26 August 2020, Available online 2 September 2020, Version of Record 12 September 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113925