Explicit methods for attribute weighting in multi-attribute decision-making: a review study

Julio Pena*, Gonzalo Nápoles, Yamisleydi Salgueiro

*Corresponding author for this work

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    Attribute weighting is a key aspect when modeling multi-attribute decision analysis problems. Despite the large number of proposals reported in the literature, reaching a consensus on the most convenient method for a certain scenario is difficult, if not impossible. As a first contribution of this paper, we propose a categorization of existing methodologies, which goes beyond the current taxonomy (subjective, objective, hybrid). As a second contribution, supported by the new categorization, we survey and critically discuss the explicit weighting methods (which are closely related to the subjective ones). The critical discussion allows evaluating how much a solution can deviate from the expected one if no foresight is taken. As a final contribution, we summarize the main drawbacks from a global perspective and propose some insights to correct them. Such a discussion attempts to improve the reliability of decision support systems involving human experts.
    Original languageEnglish
    Pages (from-to)3127-3152
    Number of pages26
    JournalArtificial Intelligence Review
    Volume53
    Issue number5
    DOIs
    Publication statusPublished - 2020

    Fingerprint

    Dive into the research topics of 'Explicit methods for attribute weighting in multi-attribute decision-making: a review study'. Together they form a unique fingerprint.

    Cite this