IndxTAR: An Efficient Algorithm for Indexed Mining of Incremental Temporal Association Rules

Abstract

Mining temporal association rules is a very interesting topic, which is applied in many applications nowadays. In temporal databases, each item has its own lifetime period, called exhibition period, which is different from other items. With the rapid increase of databases and new transactions added, the incremental mining is introduced to solve the problem of maintaining association rules in updated databases. The existing algorithms did not utilize the previously discovered rules when the database is updated .This paper presents an efficient algorithm for mining incremental temporal association rules. The proposed algorithm, called IndxTAR, utilizes two major components: a relatively new data structure and previously discovered frequent temporal itemsets to improve the performance of mining the incremental temporal association rules. Experiments on both real and synthetic datasets are conducted to compare IndxTAR algorithm performance with recently cited incremental temporal mining algorithms. The results show that IndxTAR algorithm overcomes other algorithms by many orders of magnitude and can efficiently process large databases with linear scalability.