ABAC: Alternative by alternative comparison based multi-criteria decision making method. (1st December 2022)

• Record Type: Journal Article
• Authors: Biswas, Amit; Baranwal, Gaurav; Kumar Tripathi, Anil
• Is Part Of: Expert systems with applications. Volume 208(2022)
• Publication Date: 2022-12-01
• Subjects: Multi-criteria decision-making (MCDM) -- Multi-attribute decision-making (MADM) -- Ranking -- Rank reversal -- Decision analysis; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.118174
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: A new Multi-Criteria Decision-Making Method, ABAC, is proposed. ABAC is simple, more scalable and free from rank reversal problem. ABAC is illustrated and validated using cloud service selection. Various case studies using ABAC in different domains are provided. Abstract: Decision-making appears as a complex and challenging task when it requires finding the most suitable alternative among the numerous alternatives in the presence of multiple, usually conflicting criteria. At the same time, stakeholders expect a simple, transparent, and traceable decision-making method. Multi-Criteria Decision-Making (MCDM) methods rank the alternatives considering multiple criteria. The rank reversal problem is an important issue in most existing conventional MCDM methods. This paper proposes a new alternative by alternative comparison-based MCDM Method (ABAC) that addresses the rank reversal problem. We prove that ABAC is free from the rank reversal problem. To illustrate and validate ABAC, we have taken the cloud service selection problem as an application. Further, to show the effectiveness of ABAC, we have provided several case studies covering various domains. We perform several experiments by simulating the ABAC method. We have compared ABAC and existing MCDM methods. The experimental results support that the ABAC method is a rank reversal free MCDM method. We also carry out sensitivity analysis for ABAC. Salient features of ABAC over existing MCDM methods are (i) it is simple; (ii) it is rank reversal free; (iii) it is more scalable.