Integration of unsupervised and supervised machine learning algorithms for credit risk assessment

作者：

Highlights：

• The model helps improve efficiency and accuracy of credit risk assessment.

• The proposed ensemble strategy combines SOM and seven supervised learning methods.

• The ensemble strategy helps improve the performance of credit scoring models.

• The proposed ensemble strategy was tested on three real world datasets.

摘要

•The model helps improve efficiency and accuracy of credit risk assessment.•The proposed ensemble strategy combines SOM and seven supervised learning methods.•The ensemble strategy helps improve the performance of credit scoring models.•The proposed ensemble strategy was tested on three real world datasets.

论文关键词：Credit scoring,Ensemble model,Unsupervised machine learning,Supervised machine learning,Kohonen's self-organizing maps (SOM)

论文评审过程：Received 18 November 2018, Revised 22 February 2019, Accepted 24 February 2019, Available online 19 March 2019, Version of Record 6 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.02.033