Partition Algorithm for Updating Discovered Association Rules in Data Mining

데이터마이닝에서 기존의 연관규칙을 갱신하는 분할 알고리즘

  • 이종섭 (한양대학교 산업공학과) ;
  • 황종원 (이알정보기술연구소 부소장) ;
  • 강맹규 (한양대학교 산업공학과)
  • Published : 2000.02.01

Abstract

This study suggests the partition algorithm for updating the discovered association rules in large database, because a database may allow frequent or occasional updates, and such update may not only invalidate some existing strong association rules, but also turn some weak rules into strong ones. the Partition algorithm updates strong association rules efficiently in the whole update database reuseing the information of the old large itemsets. Partition algorithms that is suggested in this study scans an incremental database in view of the fact that it is difficult to find the new set of large itemset in the whole updated database after an incremental database is added to the original database. This method of generating large itemsets is different from that of FUP(Fast Update) and KDP(Kim Dong Pil)

Keywords