We show how a logic-based database language can support the various steps of the KDD process by providing:a high degree of expressiveness,the ability to formalize the overall KDD process and teh capability of separating the concerns between the specification level and the mappling to the underlying databases and datamining tools.We generalize the notion of Inductive Data Bases proposed in [4,12] to the case Deductive Databases.In out proposal,deductive databases resemble relational databases while user defined aggregates proviede by the deductive database language resemble the mining function and results.In the paper we concentrate on association rules and show how the mechanism of user defined aggregates allows to specify the mining evaluation functions and the returned patterns.
展开▼
