A comprehensive evaluation model based on combined effect

The paper presents a method to integrate the combination effects of attributes into decision-making. First, the positive region in rough sets is employed as the knowledge carrier of the decision information system. Then the joint significance measure is constructed according to the changes of knowledge carrier induced by the attributes. Further, the combined effect matrix is given, from which the weight factors of attributes are calculated. It is different from general incidence matrix in that it reflects the combined effect of any two attributes from the perspective of the knowledge discovery. In addition, we propose a comprehensive evaluation model based on the combined effect (MBCE) for decision-making. Finally, an example is given to illustrate the feasibility and the validity of the method.