A hybrid heuristic approach for attribute-oriented mining

摘要

We present a hybrid heuristic algorithm, clusterAOl, that generates a more interesting generalised table than obtained via attribute-oriented induction (AOI). AOI tends to overgeneralise as it uses a fixed global static threshold to cluster and generalise attributes irrespective of their features, and does not evaluate intermediate interest-ingness. In contrast, clusterAOl uses attribute features to dynamically recalculate new attribute thresholds and applies heuristics to evaluate cluster quality and intermediate interestingness. Experimental results show improved interestingness, better output pattern distribution and expressiveness, and improved runtime.