Extreme learning machines for credit scoring: An empirical evaluation

作者：

Highlights：

• Extreme learning machines (ELM) are a new vehicle for credit risk management.

• Systematic analysis of ELM usability, efficiency and forecast accuracy is performed.

• Benchmark results confirm ELM effectiveness for individual and ensemble scorecards.

摘要

•Extreme learning machines (ELM) are a new vehicle for credit risk management.•Systematic analysis of ELM usability, efficiency and forecast accuracy is performed.•Benchmark results confirm ELM effectiveness for individual and ensemble scorecards.

论文关键词：Credit scoring,Artificial neural networks,Extreme learning machines,Classifier ensembles

论文评审过程：Received 6 July 2016, Revised 18 May 2017, Accepted 19 May 2017, Available online 19 May 2017, Version of Record 25 May 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.05.050