Variable precision rough set for group decision-making: An application

This study uses the variable precision rough set (VPRS) model as a tool to support group decision-making (GDM) in credit risk management. We consider the case that the classification in decision tables consisting of risk exposure (RE) may be partially erroneous, and use a variable precision factor βk to adjust the classification error. In this paper, we firstly combine VPRS and AHP to obtain the weight of condition attribute sets decided by each decision-maker (DM). Then, the integrated risk exposure (IRE) of attributes is obtained based on the three VPRS-based models. Subsequently, a new procedure of obtaining βk-stable intervals for DMk is investigated. To verify the effectiveness of these proposed methods, an illustrative example is presented. The experimental results suggest that the VPRS-based IRE have advantages in recognizing important attributes.