In today’s globalized technological area, aligning decisions with customer preferences is crucial yet challenging due to the complexities and uncertainties involved. Multi-Criteria Decision Analysis (MCDA) serves as a vital tool for constructing support systems that cater to customer-centric trends. While existing MCDA methods vary in their calculation concepts, some prioritize ideal solutions, while others accommodate personalized preferences within dynamic decision contexts. Moreover, determining the relevance of criteria based on expert knowledge adds another layer of personalization to the evaluation process, further individualizing decision-making. However, current decision models often fail to integrate these concepts, leaving a gap in how recommendations can be enhanced when both are combined. To address these challenges, this paper introduces an innovative approach integrating Ranking Comparison and Expected Solution Point Stable Preference Ordering Towards Ideal Solution methods. This hybrid model incorporates personalization into multi-criteria evaluation, catering to individual preferences. By representing customer preferences through two distinct measures, the proposed approach ensures personalized recommendations aligned with decision-makers’ needs. The efficacy of the hybrid model was validated through its application to the electric vehicle selection problem. The verification process highlighted potential disparities compared to other multi-criteria approaches, establishing a consumer preference-based Decision Support System approach for more precise and personalized selection recommendations.
Read full abstract