A new hybrid entropy-based decision support method and its application to online shopping selection

Abstract

The current study proposes a new method called the hybrid entropy-based decision support method (named HEBM) to address multi-criteria decision making (MCDM) problems with uncertainty. In the proposed HEBM, the decision makers (DMs)’ imprecise evaluations are characterized with intuitionistic multiplicative values; weights of the criteria are generated by an improved method with hybrid entropy and cross-entropy measures; and alternatives rankings are determined by defined closeness coefficients. Simulation experiments verify the validity of the improved criteria weights generation method with hybrid entropy and cross-entropy measures. Compared with existing MCDM methods, the proposed HEBM has the following advantages: (1) it avoids the information loss and has higher accuracy; (2) the weights of the criteria derived can directly characterize the DMs’ preferences on the criteria; and (3) quantitative and qualitative information are both analyzed. Simulation experiments and comparative analyses are conducted to demonstrate the effectiveness and superiority of the proposed method. A case study of online shopping selection problems is presented to illustrate the applicability of the proposed method.