Computing Rough set and Data Mining
Abstract
Rough Set theory is a novel mathematical tool for dealing with representation, learning, ambiguity, uncertainty, and knowledge generalisation. Machine learning, information discovery, decision support systems, and pattern recognition have all made use of it. It is capable of extracting underlying rules from data. The criteria for scaling the dependability of rules is confidence. Traditionally, in rough sets theory, the method for obtaining the deduction of decision rules has always prioritised the quantity of decision rules over the cost of the rules. In this paper, we rebuild the CF1 and CF2 equations. Furthermore, the study examines the scope of student placement based on three input parameters, taking into account the effect on confidence caused by both imperfect and incompatible information.