Comparing Global and Local Weights in Multi-Criteria Decision-Making: A COMET-Based Approach

Andrii Shekhovtsov, Wojciech Sałabun, Wojciech Sałabun

2024

Abstract

In the multi-criteria decision-making (MCDM) domain, decision-makers encounter the challenge of considering multiple criteria with varying importance. While numerous methods exist to determine global weights, less attention has been given to identifying local weights for individual alternatives. Unlike global weights, local weights indicate the relevance of individual criteria in the context of a specific alternative. Global weights assume a constant linear dependence of substitutability throughout the domain, where local weights indicate a local dependence, depending on the value of all attributes of a given alternative. This paper demonstrates the usage of Characteristic Objects METhod (COMET) to determine local criteria weights and provides simulation results to show the differences in those weights. By understanding the significance of criteria for specific alternatives and their impact on the overall evaluation, local weights contribute to a more comprehensive and reliable ranking. This paper presents the necessary methodologies, describes the pseudocode algorithm, and showcases two examples of two COMET models and a simulation that utilizes the ESP-COMET approach. The simulation results highlight generalized results showing the importance of identifying local weights.

Paper Citation

in Harvard Style

Shekhovtsov A. and Sałabun W. (2024). Comparing Global and Local Weights in Multi-Criteria Decision-Making: A COMET-Based Approach. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-680-4, SciTePress, pages 470-477. DOI: 10.5220/0012360700003636

in Bibtex Style

@conference{icaart24,
author={Andrii Shekhovtsov and Wojciech Sałabun},
title={Comparing Global and Local Weights in Multi-Criteria Decision-Making: A COMET-Based Approach},
booktitle={Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2024},
pages={470-477},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012360700003636},
isbn={978-989-758-680-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Comparing Global and Local Weights in Multi-Criteria Decision-Making: A COMET-Based Approach
SN - 978-989-758-680-4
AU - Shekhovtsov A.
AU - Sałabun W.
PY - 2024
SP - 470
EP - 477
DO - 10.5220/0012360700003636
PB - SciTePress