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

被引：63

作者：

Esteve, Miriam ^{[1
]}

Aparicio, Juan ^{[1
]}

Rabasa, Alejandro ^{[1
]}

Rodriguez-Sala, Jesus J. ^{[1
]}

机构：

[1] Miguel Hernandez Univ Elche UMH, Ctr Operat Res CIO, Elche 03202, Alicante, Spain

来源：

EXPERT SYSTEMS WITH APPLICATIONS | 2020年 / 162卷

关键词：

Data envelopment analysis; Frontier analysis; Free disposal hull; Overfitting; Classification and Regression Trees; DATA ENVELOPMENT ANALYSIS; MODELS;

D O I：

10.1016/j.eswa.2020.113783

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we introduce a new methodology based on regression trees for estimating production frontiers satisfying fundamental postulates of microeconomics, such as free disposability. This new approach, baptized as Efficiency Analysis Trees (EAT), shares some similarities with the Free Disposal Hull (FDH) technique. However, and in contrast to FDH, EAT overcomes the problem of overfitting by using cross-validation to prune back the deep tree obtained in the first stage. Finally, the performance of EAT is measured via Monte Carlo simulations, showing that the new approach reduces the mean squared error associated with the estimation of the true frontier by between 13% and 70% in comparison with the standard FDH. (C) 2020 Elsevier Ltd. All rights reserved.

引用

页数：17

共 41 条

[1]

Afriat SN, 1972, INT ECON REV, V13, P568, DOI [10.2307/2525845, DOI 10.2307/2525845]

[2] Evaluating productive performance: A new approach based on the product-mix problem consistent with Data Envelopment Analysis. [J].

Aparicio, Juan ;

Pastor, Jesus T. ;

Vidal, Fernando ;

Zofio, Jose L. .

OMEGA-INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE, 2017, 67 :134-144

[3] An integrated platform for spatial data mining within a GIS environment [J].

Appice, Annalisa ;

Lanza, Antonietta ;

Malerba, Donato .

2007 IEEE 23RD INTERNATIONAL CONFERENCE ON DATA ENGINEERING WORKSHOP, VOLS 1-2, 2007, :507-516

[4] Nonparametric frontier estimation: A conditional quantile-based approach [J].

Aragon, Y ;

Daouia, A ;

Thomas-Agnan, C .

ECONOMETRIC THEORY, 2005, 21 (02) :358-389

[5] SOME MODELS FOR ESTIMATING TECHNICAL AND SCALE INEFFICIENCIES IN DATA ENVELOPMENT ANALYSIS [J].

BANKER, RD ;

CHARNES, A ;

COOPER, WW .

MANAGEMENT SCIENCE, 1984, 30 (09) :1078-1092

[6] The use of frontier techniques to identify efficient solutions for the Berth Allocation Problem solved with a hybrid evolutionary algorithm [J].

Barbosa, FlAvia ;

Berbert Rampazzo, Priscila C. ;

Yamakami, Akebo ;

Camanho, Ana S. .

COMPUTERS & OPERATIONS RESEARCH, 2019, 107 :43-60

[7] A survey on multi-output regression [J].

Borchani, Hanen ;

Varando, Gherardo ;

Bielza, Concha ;

Larranaga, Pedro .

WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY, 2015, 5 (05) :216-233

[8] Random forests [J].

Breiman, L .

MACHINE LEARNING, 2001, 45 (01) :5-32

[9]

Breiman L, 1984, Classification and Regression Trees, V1st, DOI DOI 10.1201/9781315139470

[10] Nonparametric frontier estimation: a robust approach [J].

Cazals, C ;

Florens, JP ;

Simar, L .

JOURNAL OF ECONOMETRICS, 2002, 106 (01) :1-25

← 1 2 3 4 5 →