On modeling data mining with granular computing

The main objective of this paper is to advocate for formal and mathematical modeling of data mining, which unfortunately has not received much attention. A framework is proposed for rule mining based on granular computing. It is developed in the Tarski's style through the notions of a model and satisfiability. The model is a database consisting of a finite set of objects described by a finite set of attributes. Within this framework, a concept is defined as a pair consisting of the intension, an expression in a certain language over the set of attributes, and the extension, a subset of the universe, of the concept. An object satisfies the expression of a concept if the object has the properties as specified by the expression, and the object belongs to the extension of the concepts. Rules are used to describe relationships between concepts. A rule is expressed in terms of the intensions of the two concepts and is interpreted in terms of the extensions of the concepts. Two interpretations of rules are examined in detail, one is based on logical implication and the other on conditional probability.