Maintenance of multi-level association rules discovery in dynamic database under a change of support threshold

An association rule mining is often performed with a dynamic database and hierarchical items. The big problem of data mining process is a maintenance association rules while the database always changing. The purpose of this study is to extend the MLUp algorithm which can maintain a multilevel association rules discovery at the same minimum support threshold. In general, several mining tasks are required to deal with different support thresholds. MLUpCS can deal with a maintaining of mining multilevel association rules in dynamic databases under the different support threshold without re-mine a whole database. The result of MLUpCS algorithm experiment has shown how better performance than ML-T2 algorithm. The experimental results show the superior performance of MLUpCS when compared with ML-T2.

I. Introduction

Apriori is the first algorithm of an association rules discovery for static databases that was developed by Agrawal et al [1]. Unfortunately, Apriori has to re-mine a whole database when new transactions are inserted. There are many researchers solved this problem by propose Apriori based algorithm [2], [3]. Fast Update algorithm (FUp) [2] is a well-known algorithm that can efficiently deal with incremental database case. Furthermore, the Incremental Maintenance of Association Rules under Support Threshold Change algorithm (IMSC) [3] is designed to maintain a change of a minimum support threshold as well. Nevertheless, both algorithms have been designed just a single level association rules discovery.