Prof. P Krishna Reddy and his student Pradeep Pallikila published a paper on Discovering Relative High Utility Itemsets in Very Large Transactional Databases Using Null-Invariant Measure at the IEEE Big Data 2021 conference. The other authors of this paper are Uday Kiran Rage, The University of Aizu; Luna J M, University of Cordoba (Spain); Philippe Fournier Viger, Shenzhen University and Toyoda Masashi, The University of Tokyo. Research work as explained by the authors:
High utility itemset mining is an important model in data mining. It involves discovering all itemsets in a quantitative transactional database that satisfy a user-specified minimum utility (minU til) constraint. M inU til controls the minimum value that an itemset must maintain in a database. Since the model evaluates an itemset’s interestingness using only the minU til constraint, it implicitly assumes that all items in the database have similar utility values. However, some items have high utility, while others may have relatively low utility in a database. If minU til is set too high, the user will miss all itemsets containing low utility items. To find itemsets that involve both high and low utility items, minU til has to be set very low. However, this may cause a combinatorial explosion as the items with high utility may combine with others in all possible ways. This dilemma is called the low utility item problem. This paper proposes a flexible model of relative high utility itemset to address this problem. We introduce a new null-invariant measure, called utility ratio, to evaluate the interestingness of an itemset in the database. We also present a fast single scan algorithm to find all desired itemsets in the database. Experimental results demonstrate that the proposed algorithm is efficient. Finally, a case study on Yahoo! JAPAN retail data shows that the proposed model is useful.
Conference page: https://bigdataieee.org/BigData2021/