A three-way decision method in a fuzzy condition decision information system and its application in credit card evaluation

Abstract

An information system as a database that represents relationships between objects and attributes is an important mathematical model in the field of artificial intelligence. A fuzzy condition decision information system(fc-decision information system) is a decision information system where each condition attribute is fuzzy. This paper proposes a three-way decision method in a fc-decision information system and gives its application in credit card evaluation. Gaussian kernel based on fuzzy Euclid distance between fuzzy sets is first acquired. Then the fuzzy $$T{\cos }$$ -equivalence relation, induced by a given fc-decision information system, is obtained using Gaussian kernel. Next, based on approximately equal relation (ae-relation) between fuzzy sets, decision-theoretic rough set model in this fc-decision information system is presented. Moreover, a three-way decision method based on this decision-theoretic rough set model is proposed by means of probability measures of sets. Finally, an example of credit card evaluation is employed to illustrate the feasibility of the proposed method.