A Systematic Review of Multi-Attribute Decision Making Methods for Modern Decision Science

Abstract

Multi-Attribute Decision Making (MADM) is a critical branch of decision science that provides structured methodologies for evaluating and selecting alternatives based on multiple conflicting criteria. In modern decision-making processes, stakeholders often encounter complex scenarios where trade-offs between criteria must be carefully analyzed. MADM techniques enable decision-makers to rank and prioritize alternatives while accounting for diverse objectives, uncertainties, and real-world constraints. This paper delves into the fundamental principles and theoretical foundations of MADM, highlighting its role in optimizing decision processes across various industries. The study explores widely adopted MADM techniques, including the Analytic Hierarchy Process (AHP), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and VIKOR, which are essential for systematically structuring and solving decision-making problems. Furthermore, it examines advanced approaches such as Neutrosophic MADM, which integrates uncertainty and indeterminacy handling to improve decision reliability. The paper comprehensively analyzes real-world applications in domains such as engineering, business management, supply chain optimization, and financial decision-making. Additionally, numerical analysis, comparative evaluations, and structured decision matrices are included to illustrate the effectiveness of different MADM methodologies. Special attention is given to the impact of weighting methods, normalization techniques, and the role of expert judgment in decision-making. Finally, the study discusses existing challenges in MADM, including subjectivity in criteria weighting, computational complexities, and data inconsistencies. Future research directions are also outlined, emphasizing the integration of Artificial Intelligence (AI), Machine Learning (ML), and big data analytics with MADM to enhance decision-making accuracy, automation, and adaptability in dynamic environments. ML, and big data analytics with MADM to enhance decision-making accuracy, automation, and adaptability in dynamic environments.