Journal
INFORMATION FUSION
Volume 50, Issue -, Pages 54-70Publisher
ELSEVIER
DOI: 10.1016/j.inffus.2018.10.003
Keywords
Multi-criteria group decision making (MCGDM); Consensus reaching process (CRP); Hesitant fuzzy linguistic term sets (HFLTSs); Expertise identification; Criteria weighting
Funding
- Moulay Ismail University
- IRESEN (Research Institute for Solar Energy and New Energies) under the research project STEEP
Ask authors/readers for more resources
The integration of a consensus reaching process (CRP) becomes paramount to make highly accepted group decisions in complex real-life multi-criteria group decision making (MCGDM) problems. Notwithstanding, existing CRPs for MCGDM do neither exhaustively analyse the diversity in decision makers' expertise levels, nor they consider that (because of such diversity) individuals might exhibit distinct perceptions on the relative importance of evaluation criteria. In this study, we present a novel expertise-based consensus building model for MCGDM under a hesitant fuzzy linguistic setting. Firstly, an expertise identification approach is devised to objectively determine the expertise degree of each decision maker based on multiple features. The proposed approach allows to dynamically assigning importance weights to the decision makers' opinions based on their expertise, as well as intelligently combining their individually elicited subjective and objective criteria weights into meaningful expertise-dependent combinative weights. Then, a CRP for MCGDM problems is introduced based on an improved consensus measurement process and an expertise-based feedback mechanism that provides a highly tailored, personalised means of direction rules to guide decision makers during the consensus building process. A numerical example is provided to illustrate the application of the CRP, and a detailed comparison analysis is presented to verify the validity and accuracy of this study's proposal.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available