Efficient weighted association rule mining using lattice
Yue Zhai, Lijuan Wang, Wang Ning · 2014
In the problem of discovering weighted association rules (WAR), the number of rules is often very large and they contain some redundant rules, the process of mining can be very time consuming. In this paper, we present an application of lattice in mining WAR which will reduce greatly the time and quantity of mining rules. Our method includes three phases: (1) Generating the frequent closed itemsets(FCI) using indiscernibility matrix. (2) Building frequent weighted closed itemsets lattice(FWCIL) based on FCI.(3) Mining WAR from lattice. It is shown by experimental results that our approach not only results in shorter average execution times, but also remove some redundant rules than the generalization of previous known methods on quantitative association rules.