Optimized transitive association rule: mining significant stopover between events

Authors:
Yasuhiko Morimoto
Affiliations:
Hiroshima University, Kagamiyama, Higashi-Hiroshima, Japan
Venue:
Proceedings of the 2005 ACM symposium on Applied computing
Year:
2005

Citing 2
Cited 1

Introduction to Algorithms

Introduction to Algorithms
Mining Sequential Patterns

ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering

Geometrical information fusion from WWW and its related information

DNIS'07 Proceedings of the 5th international conference on Databases in networked information systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider a problem of finding optimized transitive association rules. A transitive association rule is a transitive sequence of different events. Each of two consecutive events in a transitive association rule is a conventional association rule. Transitive confidence is the product of confidence values of all the association rules in the event sequence. The optimized transitive association rule from a cause event to an effect event is the optimal sequence of events whose transitive confidence is maximum among all possible sequences from the cause to the effect. In this paper, we present space efficient algorithms for computing all of the optimized transitive association rules between events, whose transitive confidence is not less than a user specified minimum confidence value.