Composite quantile regression neural network with applications
作者：
Highlights：
• We propose a novel composite quantile regression neural network model.
• The model bridges the gap between composite quantile regression and ANNs.
• It is flexible and efficient to explore nonlinear relationships among variables.
• It enables us to achieve desired results for handling different types of data.
• It outperforms practically well-known methods including standard ANNs.
摘要
•We propose a novel composite quantile regression neural network model.•The model bridges the gap between composite quantile regression and ANNs.•It is flexible and efficient to explore nonlinear relationships among variables.•It enables us to achieve desired results for handling different types of data.•It outperforms practically well-known methods including standard ANNs.
论文关键词：Quantile regression,Neural network,Quantile regression neural network,Composite quantile regression,CQRNN
论文评审过程：Received 6 December 2015, Revised 29 January 2017, Accepted 30 January 2017, Available online 31 January 2017, Version of Record 7 February 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.01.054
