Adaptive semi-supervised consensus model for multi-criteria large group decision making in a linguistic setting

Abstract

University of Bristol -Explore Bristol Research General rightsThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Abstract-In this paper we investigate the consensus reaching problem for Large Group Multi-Criteria Decision Making (MCLGDM). We present an adaptive, semi-supervised consensus model for MCLGDM problems with preferences expressed as Comparative Linguistic Expressions. Specifically, our work introduces an adaptive, semi-supervised feedback mechanism that, depending on the positions of decision makers' preferences and their level of uncertainty caused by hesitancy, requests human supervision to modify their preferences or updates them automatically. The proposed consensus model effectively handles large amounts of linguistic-natured information in consensus processes involving large groups. The methodology is illustrated and experimentally validated through a MCLGDM problem for candidate assessment in recruiting processes. Likewise, a theoretical comparison with similar works is provided.

Smart Contract-based Consensus Building for Collaborative Medical Decision-Making

“…If the consensus degree exceeds the threshold (CD c(r) > threshold), the group moves on to the selection phase; otherwise, the consensus builder takes appropriate steps to increase the level of agreement in the following consensus round. This can be done in different ways including through an interactive feedback process [13] and automatic adjustment of the participants' preferences [25]. Consensus must be achieved before a maximum predefined number of iterations r max is surpassed, i.e., the process continues until CD c(r) ≥ threshold or r > r max .…”

Proposta de um modelo híbrido de tomada de decisão em grupo baseado na teoria >i<dual hesitant fuzzy>/i< e algoritmo genético

“…Romero-Gelvez, e Garcia-Melon ( 2016) " A consensus reaching process in a Group Decision Making (GDM) problem is an iterative process composed by several discussion rounds in which experts are expected to modify their preferences according to the advice given by a facilitator." Palomares et al, (2017) "… bringing DMs preferences closer to each other before making a decision"…”