Pushing regularity constraint on high utility itemsets mining

High utility itemsets mining (HUIM) is an interesting topic in data mining which can be applied in a wide range of applications, for example, on retail marketing-finding sets of sold products giving high profit, low cost, etc. However, HUIM only considers utility values of items/itemsets which may be insufficient to observe buying behavior of customers. To address this issue, we here introduce an approach to add regularity constraint into high utility itemsets mining. Based on this approach, sets of co-occurrence items with high utility values and regular occurrence, called high utility-regular itemsets (HURIs), are regarded as interesting itemsets. To mine HURls, an efficient single-pass algorithm, called HURI-UL, is proposed. HURI-UL applies concept of remaining and overestimated utilities of itemsets to early prune search space (uninteresting itemsets) and also utilizes utility list structure to efficiently maintain utility values and occurrence information of itemsets. Experimental results on real datasets show that our proposed HURI-UL is efficient to discover high utility itemsets with regular occurrence.