An Approach for Attribute Weights Acquisition based on Rough Sets Theory and Information Gain

Abstract

The irrationality of constructing weights, lending to subjectivity and without considering the redundancy of attributes, exists in traditional management decision-making. The σ − important rating and ξ − important rating are first proposed by the attribute reduct in rough sets theory. Then, the g − important rating is given by the information gain in information entropy. An approach for acquiring attribute weights employing the three important ratings is presented to solve the problem of subjectivity and redundancy. An empirical case study validates the rationality and validity of our method.