Development of Multi-Attribute Utility Theory Methods in Dynamic Decision Models Using Change-Data Driven

The determination of the weight of criteria is a crucial element in multi-criteria decision making because weights reflect the relative importance of each criterion to the decision maker's ultimate goal.Development of the Multi-Attribute Utility Theory (MAUT) method with change-driven objective weighting can significantly improve the accuracy and objectivity of decision making, with dynamically adjusting the weighting of criteria based on changes in environment or preferences, change-driven objective weighting allows for more precise evaluation of decision alternatives.The final utility ranking results of each vendor using the MAUT development show that Vendor 6 occupies the first position with the highest utility value of 0.646, indicating that this vendor has the best performance based on the given criteria.The results of the sensitivity analysis using Pearson's correlation for each weight change ranging from 0.1 to 0.5, obtained a high correlation coefficient of 1 which shows that the vendor rating is very sensitive to changes in criterion weights.Future research from the development of the MAUT method can be directed at several innovative aspects to increase its relevance and application.One of the focuses is integration with advanced weighting methods, such as machine learning-based approaches or hybrid entropy, to improve the objectivity and flexibility of decision analysis.