Efficiency analysis trees: A new methodology for estimating production frontiers through decision trees

作者：

Highlights：

• A relationship between Machine learning and frontier efficiency analysis is stated.

• A method based on regression trees is introduced for estimating production frontiers.

• The new method guaranties the satisfaction of free disposability.

• The problem of overfitting is solved.

• A Monte Carlo experience shows that the new method outperforms FDH.

摘要

•A relationship between Machine learning and frontier efficiency analysis is stated.•A method based on regression trees is introduced for estimating production frontiers.•The new method guaranties the satisfaction of free disposability.•The problem of overfitting is solved.•A Monte Carlo experience shows that the new method outperforms FDH.

论文关键词：Data envelopment analysis,Frontier analysis,Free disposal hull,Overfitting,Classification and Regression Trees

论文评审过程：Received 10 December 2019, Revised 19 June 2020, Accepted 19 July 2020, Available online 29 July 2020, Version of Record 5 August 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113783