A novel multiple attribute decision making method based on grey relational projection and its application for e-commerce risk assessment

Abstract

With respect to multiple attribute decision making (MADM) problems in which the attribute values take the form of hesitant fuzzy elements, the traditional grey relational projection (GRP) method is extended to solve multiple attribute decision making problems under hesitant fuzzy environment. Since the weights of attributes are incompletely known, a nonlinear optimisation model is established, i.e., a reasonable weight vector of attributes should make all alternatives have the largest grey relational projections on positive ideal solution and the smallest grey relational projections on negative ideal solution. Then, based on the hesitant fuzzy decision matrix provided by decision makers, all feasible alternatives are ranked according to the descending order of relative grey relational projections and the most desirable alternative(s) should have the largest grey relational projection on positive ideal solution and the smallest grey relational projection on negative ideal solution. Finally, a numerical example of e-commerce risk assessment is given to illustrate the application of the proposed method.