Computing Rule Confidence using Rough set and Data Mining

Rough Set theory is a new mathematical tool to deal with representation, learning, vagueness, uncertainty and generalization of knowledge. It has been used in machine learning, knowledge discovery, decision support system s and pattern recognition. It can abstract underlying rules from data. Confidence is the criterion to scaling the reliability of rules. Traditionally, the algorithm to obtain the deduction of decision rule in rough sets theory always take more into account of the number of decision rules than the cost of the rules. In this study, we reconstruct the formulae for CF1 and CF2. Further, the study is the scope of placement of students based on three input parameters, which considers effect on confidence caused by both imperfect and incompatible information.