Package elki.itemsetmining.associationrules.interest

Association rule interestingness measures.

Much of the confusion with these measures arises from the anti-monotonicity of itemsets, which are omnipresent in the literature.

In the itemset notation, the itemset X denotes the set of matching transactions {T|XT} that contain the itemset X. If we enlarge Z=XY, the resulting set shrinks: {T|ZT}={T|XT}{T|YT}.

Because of this: support(XY)=P(XY) and support(XY)=P(XY). With "support" and "confidence", it is common to see the reversed semantics (the union on the constraints is the intersection on the matches, and conversely); with probabilities it is common to use "events" as in frequentist inference.

To make things worse, the "support" is sometimes in absolute (integer) counts, and sometimes used in a relative share.