Maintenance of Association Rules in Data Mining

Abstract

In real-world applications, developing a mining algorithm that can incrementally maintain discovered information as a database grows is quite important. In the past, we proposed an incrementally mining algorithm that used a lower support threshold and an upper support threshold to reduce the need for rescanning original databases and to save maintenance costs. In this paper, we extend it and propose a new incrementally mining algorithm also based on the upper and lower thresholds. The number of new transactions allowed for not rescanning databases is fixed, and the lower support threshold is dynamically set close to the upper support threshold, making the additional overhead decreasing in maintaining the consistency of association rules with the updated databases