HEWIN: HIGH EXPECTED WEIGHTED ITEMSET MINING IN UNCERTAIN DATABASES

Abstract

In recent years, many algorithms have been proposed to discover frequent itemsets over uncertian databases or mine weighted based frequent itemsets from precisely binary databases. None of the above algorithms have been, however, designed to discover interesting patterns by considering both weight and data uncertainty constraints. In this paper, a novel knowledge called high expected weighted itemsets (HEWIs) is designed to reveal more useful and meaningful information by considering both the weight and existential probability constraints over an uncertain database. A two-phase HEWI-UTP algorithm is developed to overestimate the high upper-bound expected-weighted itemsets (HUBEWIs) based on the developed high upper-bound expected weighted downward closure property, which can be used to reduce the search space for discovering HEWIs. An extensive experimental study carried on several real-life and synthetic datasets shows the performance of the proposed algorithm.