Hesitant fuzzy network topsis methods with the incorporation of z-numbers and social network analysis for small and large scale group decision making
It is critical to arrive at an acceptable level of consensus in a group for an agreeable and implementable decision. The evaluation of alternatives in conventional TOPSIS decision making does not take into account the inherent vagueness of information as it requires a systematic decision-making proc...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://etd.uum.edu.my/10153/1/s826026_01.pdf https://etd.uum.edu.my/10153/2/s826026_02.pdf https://etd.uum.edu.my/10153/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | It is critical to arrive at an acceptable level of consensus in a group for an agreeable and implementable decision. The evaluation of alternatives in conventional TOPSIS decision making does not take into account the inherent vagueness of information as it requires a systematic decision-making process in which relies on numerous
conditions and unpredictable situations. It is common in deciding the best choice with the highest satisfaction degree that are evaluated based on attributes. However, two or more alternatives with the same or nearest satisfaction degree would lead to hesitancy in the decision. Thus, fuzzy network TOPSIS is incorporated with the hesitant fuzzy set is developed namely hesitant fuzzy network TOPSIS. Nevertheless, the reliability of decisions by experts and the complexity in large scale are less highlighted in hesitant fuzzy network TOPSIS. Therefore, this study aims in formulating hesitant fuzzy network TOPSIS with the incorporation of Z-numbers.
The formulation also implies social network analysis for large-scale group decision making. In this study, four new fuzzy network TOPSIS are developed in small scale and large-scale group decision making. The proposed methods enhance the transparency and reliability by incorporating fuzzy network and Z numbers respectively. In addition, social network analysis is suitable for dealing with the complexity involved in large scale group decision making. For the practicality and
the effectiveness of the proposed methods in a realistic scenario, a case study of stock selection and the analysis of results comparing proposed methods to the established methods has been considered. The ranking of the proposed methods are validated comparatively using performance indicators namely Spearman rho correlation, Root Means Squared Error, and Absolute Distance by assuming ranking
based on Return on Investment as a benchmarking. Based on the case study, the proposed methods outperform the established methods in terms of average rank position. In conclusion, the proposed methods contribute significantly toward the implementation of small scale and large scale group decision making using hesitant
fuzzy set, fuzzy network and Z numbers. |
|---|