MINING ASSOCIATION RULES AND EXTENDED CONCEPT LATTICE

摘要

Mining association rules is an important problem in KDD. The Extended Concept Lattice (ECL), got by introducing equivalence intension into the Concept lattice, is a novel and efficient tool for data analysis and knowledge discovery in databases. It is an extended form of the Concept lattice. In this paper, the problem of mining association rules based on the ECL is discussed, and the notion of the frequent concept sub-lattice (FCSL) is proposed. It demonstrates that how to generate all high confidence rules from an example database of transactions using the FCSL.