Predicting group membership of sustainable suppliers via data envelopment analysis and discriminant analysis

Mohammad Tavassoli*, Reza Farzipoor Saen

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

26 Citations (Scopus)

Abstract

Given the fierce competition between large companies, the sustainable supply chain has been recognized as a key component of corporate responsibility in recent years. Classification of suppliers can facilitate the selection of a suitable supplier for management, which saves time and costs for the company. Data envelopment analysis (DEA) has become one of the most frequently applied tools for measuring the relative efficiency of suppliers. Standard DEA models assume that the data are deterministic. But, in many real life applications not all inputs and/or outputs are deterministic, some could be stochastic. Additionally, existence of zero data in stochastic DEA models can be a new assumption in performance evaluation of suppliers. In this paper we proposed a novel super-efficiency stochastic DEA model for measuring relative efficiency of suppliers in presence of zero data. By proposed model, all suppliers are classified into two efficient and inefficient groups based on their efficiency score. Then, to predict group membership of new supplier, a novel Stochastic MIP model is presented. The results of this study indicate the high accuracy of prediction by the proposed model. In order to application of the proposed approach, a case study is presented.

Original languageEnglish
Pages (from-to)41-52
Number of pages12
JournalSustainable Production and Consumption
Volume18
DOIs
Publication statusPublished - Apr 2019

Keywords

  • Data envelopment analysis (DEA)
  • Discriminant analysis (DA)
  • Infeasibility
  • Stochastic data
  • Sustainable supplier

ASJC Scopus subject areas

  • Environmental Engineering
  • Environmental Chemistry
  • Renewable Energy, Sustainability and the Environment
  • Industrial and Manufacturing Engineering

Cite this