SITW Method: A New Approach to Re-identifying Multi-criteria Weights in Complex Decision Analysis

Abstract

Multi-Criteria Decision Analysis (MCDA) addresses complex decision-making problems across various fields such as logistics, management, medicine, and sustainability. MCDA tools provide a structured approach to evaluating decisions with multiple conflicting criteria, assisting decision-makers in navigating intricate scenarios. Engaging experts is crucial for identifying multi-criteria models due to the diverse aspects of decision-making problems. Techniques such as pairwise comparisons and criterion weight assignment are commonly used to incorporate expert knowledge into decision models. Criterion weight assignment allows experts to indicate the importance of each criterion; however, issues can arise if model parameters are lost or experts become unavailable. To mitigate these issues, techniques like entropy or standard deviation can determine weights without direct expert input. In this context, the Stochastic Identification of Weights (SITW) method utilizes existing assessment samples to re-identify models and obtain weights that replicate the rankings of a reference model. This study compares information-based methods (Entropy, STD) with the SITW method in re-identifying the TRI medical function as a benchmark. The effectiveness of these methods is evaluated using Spearman's weighted correlation coefficient across various scenarios and alternative numbers. Results indicate that the SITW method provides more significant results than other methods in identifying multi-criteria weights by leveraging previously evaluated alternatives. Future research could explore broader approaches and uncertainty scenarios to ensure comprehensive decision support in complex contexts.