Improving preference disaggregation in multicriteria decision making: Incorporating time series analysis and a multi-objective approach

Abstract

Preference disaggregation analysis (PDA) is an approach in multicriteria decision analysis that aims to extract preferential information from holistic judgments provided by decision-makers. This paper presents an original methodology for PDA that addresses two challenges in this field. First, we consider the structure of the data as a tensor within the context of PDA to capture decision-makers' preferences based on descriptive measures of the criteria time series, such as trend and average. This approach enables an understanding of decision-makers' preferences in scenarios involving time series analysis, which is common in medium- to long-term impact decisions. Second, the paper addresses the robustness concern in PDA methods, which involves dealing with multiple compatible models reflecting the decision-maker's preferences, using a multi-objective model. This approach allows for identifying multiple preference models and provides a mechanism to converge towards the most likely preference model. The proposed method is evaluated using real data. Results show that the decision-maker's preference for a criterion can vary based on descriptive measures. This highlights the importance of considering both the criterion and the descriptive measures in the decision problem. The multi-objective analysis produces multiple solutions and, under specific conditions, can lead to a single solution reflecting the decision-maker's preferences.