Journal
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
Volume 264, Issue 2, Pages 453-461Publisher
ELSEVIER SCIENCE BV
DOI: 10.1016/j.ejor.2017.08.006
Keywords
Multi criteria decision analysis; Preference modeling; PROMETHEE method; Partial information; Surrogate weights
Funding
- Brazilian Research Council (CNPq) [309906/2013-0, 309143/2014-4, 465566/2014-6, 308531/2015-9, 408944/2016-1]
Ask authors/readers for more resources
One of the main tasks in a multi-criteria decision-making process is to define weights for the evaluation criteria. However, in many situations, the decision-maker (DM) may not be confident about defining specific values for these weights and may prefer to use partial information to represent the values of such weights with surrogate weights. Although for the additive model, the use of surrogate weighting procedures has been already explored in the literature, there is a gap with regard to experimenting with such kind of preference modeling in outranking based methods, such as PROMETHEE, for which there already are applications with surrogate weights in the literature. Thus, this paper presents an experimental study on, preference modeling based on simulation so as to increase understanding and acceptance of a recommendation obtained when using surrogate weights within the PROMETHEE method. The main approaches to surrogate weights in the literature (EW, RS, RR and ROC) have been evaluated for choice and ranking problematics throughout statistical procedures, including Kendall's tau coefficient. The surrogate weighting procedure that most faithfully represents a DM's value system according to this analysis is the ROC procedure. (C) 2017 Elsevier B.V. All rights reserved.
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