Application of Credibility Coefficients Based on Decision Rules

Abstract

Credibility coefficients reflect similarity of objects in respect to other ones in information systems. For decision tables we can use credibility coefficients based on decision rules. Knowledge discovery methods can extract rules from an information system. The knowledge represented by the rules may be not exact due to improper data. Calculation of credibility coefficients is based on an assumption that majority of data is correct and only a minor part may be improper. The main purpose of using credibility coefficients is to indicate to which group a particular object probably belongs. A main focus of the paper is set on an algorithm of calculating credibility coefficients and a presentation how credibility coefficients can be used. The algorithm of presented credibility coefficients is based on decision rules, which are generated using the rough set theory. Some remarks on practical results of identifying improper data by credibility coefficients are inserted in the paper as well.