Three-stage performance modeling using DEA–BPNN for better practice benchmarking
作者：
Highlights：
• DEA stratification and grouping of DMUs to form hierarchical frontiers.
• BPNN learning of efficiency patterns and classification of frontiers.
• BPNN prediction of incremental improvement outputs.
• The three-stage model for innovative ‘better practice benchmarking’.
• Empirically validated by using healthcare data.
摘要
•DEA stratification and grouping of DMUs to form hierarchical frontiers.•BPNN learning of efficiency patterns and classification of frontiers.•BPNN prediction of incremental improvement outputs.•The three-stage model for innovative ‘better practice benchmarking’.•Empirically validated by using healthcare data.
论文关键词：Backpropagation neural network,Better practice benchmarking,Data envelopment analysis,Three-stage model
论文评审过程：Received 14 January 2016, Revised 30 September 2016, Accepted 5 November 2016, Available online 5 November 2016, Version of Record 23 December 2016.
论文官网地址：https://doi.org/10.1016/j.eswa.2016.11.009
