Comparative Effectiveness of Data Normalization Methods in ARAS for Multi-Criteria Decision-Making Across Industrial Applications

Authors

  • Anita Kumari Department of Production and Industrial Engineering, Birla Institute of Technology: Mesra, Ranchi, India
  • Bappa Acherjee Department of Production and Industrial Engineering, Birla Institute of Technology: Mesra, Ranchi, India

DOI:

https://doi.org/10.23055/ijietap.2025.32.4.10995

Keywords:

Multi-Criteria decision making

Abstract

Multi-criteria decision-making (MCDM) utilizes various tools and methods to enhance decision-making across fields such as engineering, materials, manufacturing, and management. Data normalization is a crucial step in MCDM for converting criteria values to a standard scale, enabling accurate rating and ranking of alternatives. Selecting the appropriate data normalization method from various available options remains challenging yet crucial for effective decision-making across industrial applications. In this study, ten data normalization methods (DNMs) are evaluated with the ARAS (Additive Ratio Assessment) method, and their selection for enhancing robustness in MCDM is investigated. The suitability of each DNM is assessed through various test cases and sensitivity analyses, examining the impact of normalization on decision-making results. A comparative analysis of DNMs is performed using Spearman’s rank correlation, criteria weight variations, dynamic matrices, and plurality voting to identify the most effective data normalization methods. The findings from this study offer comprehensive insights into how different DNMs influence the performance of the ARAS method, providing practical guidance for improving decision-making accuracy across industrial applications. Through this process, four additional DNMs are identified as suitable for integration with the ARAS method, expanding its application scope beyond the traditional sum-based linear normalization method.

Published

2025-08-11

How to Cite

Kumari, A., & Acherjee, B. (2025). Comparative Effectiveness of Data Normalization Methods in ARAS for Multi-Criteria Decision-Making Across Industrial Applications. International Journal of Industrial Engineering: Theory, Applications and Practice, 32(4). https://doi.org/10.23055/ijietap.2025.32.4.10995

Issue

Section

Operations Research/Management Science