Mining Level-Crossing Association Rules from Large Databases

Abstract

Existing algorithms for mining association rule at multiple concept level, restricted mining strong association among the concept at same level of a hierarchy. However mining level-crossing association rule at multiple concept level may lead to the discovery of mining strong association among at different level of hierarchy. In this study, a top-down progressive deepening method is developed for mining level-crossing association rules in large transaction databases by extension of some existing multiple-level association rule mining techniques. This method is using concept of reduced support and refine the transaction table at each level.