IGB : a new informative generic base of association rules

The problem of the relevance and the usefulness of extracted association rules is becoming paramount, since an overwhelming number of association rules may be derived from even reasonably sized real-life databases. A possible solution consists in using results of Formal Concept Analysis to generate a generic base of association rules. This set, of reduced size, makes it possible to derive all the association rules via an adequate axiomatic system. In this paper, we introduce a novel generic and informative base of association rules, conveying two types of knowledge: “factual” and “implicative”. We present also a valid and complete axiomatic system allowing to derive the set of all association rules. Results of the experiments carried out on real-life databases showed important profits in terms of compactness of the introduced generic base.