Probabilistic decision tables in the variable precision rough set model

摘要

The Variable Precision Rough Set Model(VPRS) is an extension of the original rough set model. This extension is directed towards deriving decision table-based predictive models form data with para- Metrically adjustable degrees of accuracy. The imprecise nature of such models leads to quite significant Modification of the classical notion of decision table. This is accomplished by introducing the idea of Approximation region-based, or probabilistic decision table which is a tabular specification of three, in General uncertain, disjunctive decision rules corresponding to rough approximation regions; positive, Boundary and negative regions. The focus of the paper is on the extraction of such decision tables from Data, their relationship to conjunctive rules and probabilistic assessment of decision confidence with such Rules.