A novel outranking based multi criteria group decision making methodology integrating ELECTRE and VIKOR under intuitionistic fuzzy environment


Cali S., Balaman S. Y.

EXPERT SYSTEMS WITH APPLICATIONS, cilt.119, ss.36-50, 2019 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 119
  • Basım Tarihi: 2019
  • Doi Numarası: 10.1016/j.eswa.2018.10.039
  • Dergi Adı: EXPERT SYSTEMS WITH APPLICATIONS
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.36-50
  • Anahtar Kelimeler: Multi criteria decision making, Intuitionistic fuzzy set theory, ELECTRE, VIKOR, Product/service ranking, Group decision making
  • Dokuz Eylül Üniversitesi Adresli: Evet

Özet

This study proposes a new group decision making (GDM) methodology to solve outranking problems efficiently under uncertainty integrating multi criteria decision making (MCDM) and intuitionistic fuzzy set (IFS) theory. To this aim, ELECTRE I, an outranking based MCDM approach is extended with VIKOR method, an ideal solution based approach, under intuitionistic fuzzy environment. The methodology utilizes pairwise comparison and outranking relation concepts of ELECTRE methods to construct different concordance and discordance sets in order to reflect preferences of decision makers effectively. By the help of similarities between concordance and discordance characteristics of ELECTRE and maximum group utility and minimum individual regret characteristics of VIKOR, the methodology enables the intuitionistic fuzzy ELECTRE to overcome its weakness in ranking process and presents complete ranking. In addition, this study employs entropy method to identify the weights of criteria and decision makers, and weighted distance approach to determine the weights of different concordance sets. Utilizing these methods leads to specifying these weights objectively. The applicability of the proposed approach is explored by an illustrative example on supplier selection problem by explaining the method step by step. Furthermore, four computational experiments are conducted in order to demonstrate its applicability to the other areas and the results are compared. (C) 2018 Elsevier Ltd. All rights reserved.