An adaptive entropy-Heronian fuzzy outranking framework for multi-criteria decision analysis

Decision-making problem that involves multiple criteria are often affected by uncertainty, vague assessments, and diverse sources of information. These challenges have been overcome in this paper by introducing an entropy–Heronian outranking framework for fuzzy multi-criteria decision-making problems. Triangular fuzzy numbers represent the evaluations of criteria to capture linguistic uncertainty. In addition, entropy theory is employed to derive objective criterion weights based on the dispersion of evaluation data. In this paper, the Heronian mean is incorporated into the aggregation process within the outranking framework to take into consideration the possible interaction between criteria. Furthermore, data-driven statistical techniques are employed to estimate preference and indifference thresholds, and by including the interquartile range and the standard deviation as statistical parameters, the subjectivity in parameter selection will be reduced. This paper presents a case study of a sustainability evaluation to demonstrate the application of the proposed model. A comparative analysis with well-known fuzzy MCDM methods shows that the proposed model produces reliable and consistent ranking results. Furthermore, the model's robustness across different conditions is confirmed by a sensitivity analysis that examines the influence of threshold parameters on the final decision outcomes. Overall, the proposed model provides a structured, data-driven approach to handling uncertainty and improving decision consistency in fuzzy multi-criteria environments.