Robust worst-practice interval DEA with non-discretionary factors

Aliasghar Arabmaldar, Emmanuel Kwasi Mensah, Mehdi Toloo*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)

Abstract

Traditionally, data envelopment analysis (DEA) evaluates the performance of decision-making units (DMUs) with the most favorable weights on the best practice frontier. In this regard, less emphasis is placed on non-performing or distressed DMUs. To identify the worst performers in risk-taking industries, the worst-practice frontier (WPF) DEA model has been proposed. However, the model does not assume evaluation in the condition that the environment is uncertain. In this paper, we examine the WPF-DEA from basics and further propose novel robust WPF-DEA models in the presence of interval data uncertainty and non-discretionary factors. The proposed approach is based on robust optimization where uncertain input and output data are constrained in an uncertainty set. We first discuss the applicability of worst-practice DEA models to a broad range of application domains and then consider the selection of worst-performing suppliers in supply chain decision analysis where some factors are unknown and not under varied discretion of management. Using the Monte-Carlo simulation, we compute the conformity of rankings in the interval efficiency as well as determine the price of robustness for selecting the worst-performing suppliers.

Original languageEnglish
Article number115256
JournalExpert Systems with Applications
Volume182
DOIs
Publication statusPublished - Nov 15 2021

Keywords

  • Interval DEA
  • Non-discretionary factors
  • Robust optimization
  • Supplier selection
  • Worst-practice DEA

ASJC Scopus subject areas

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this