Lee Do Heon, Cho Il Rae, Kim Jong Deok

The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 4, pp. 895-907, Apr. 1997
10.3745/KIPSTE.1997.4.4.895,   PDF Download:

Abstract

The mining of association rules discovers the tendency of events occurring simultaneously in large databases. Previously announced research on association rules deals with associations with respect to the whole transaction. However, some association rules could have very high confidence in a sub-range of the time domain, even though they do not have quite high confidence in the whole time domain. Such kind of association rules are expected to be very useful in various decision making problems. In this paper, we define transient association rule, as an association with high confidence worthy of special attention in a partial time interval, and propose an efficient algorithm which finds out the time intervals appropriate to transient association rules from large databases. We propose the data-driven retrieval method excluding unnecessary interval search, and design an effective data structure manageable in amin memory obtained by one scanning of database, which offers the necessary information to next retrieval phase. In addition, our simulation shows that the suggested algorithm has reliable performance at the time cost acceptable in application areas.

Statistics
Cite this article