A Framework for Mining Interesting Pattern Sets
This paper suggests a framework for mining subjectively in- teresting pattern sets that is based on two components: (1) the encoding of prior information in a model for the data miner’s state of mind; (2) the search for a pattern set that is maximally informative while eﬃcient to convey to the data miner. We illustrate the framework with an instantiation for tile patterns in binary databases where prior information on the row and column marginals is available. This approach im- plements step (1) above by constructing the MaxEnt model with respect to the prior information [2, 3], and step (2) by relying on concepts from information and coding theory. We provide a brief overview of a number of possible ex- tensions and future research challenges, including a key chal- lenge related to the design of empirical evaluations for sub- jective interestingness measures.