Mining association rules on significant rare data using relative support

被引：85

作者：

Yun, HY

Ha, DS

Hwang, BY

Ryu, KH ^{[1
]}

机构：

[1] Chungbuk Natl Univ, Sch Elect & Comp Engn, Cheongju 361763, South Korea

[2] Chonnam Natl Univ, Dept Comp Sci, Kwangju, South Korea

[3] LG Elect Inc, Seoul, South Korea

来源：

JOURNAL OF SYSTEMS AND SOFTWARE | 2003年 / 67卷 / 03期

关键词：

data mining; potential information; association rules; significant rare data;

D O I：

10.1016/S0164-1212(02)00128-0

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Recently, data mining, a technique to analyze the stored data in large databases to discover potential information and knowledge, has been a popular topic in database research. In this paper, we study the techniques discovering the association rules which are one of these data mining techniques. And we propose a technique discovering the association rules for significant rare data that appear infrequently in the database but are highly associated with specific data. Furthermore, considering these significant rare data, we evaluate the performance of the proposed algorithm by comparing it with other existing algorithms for discovering the association rules. (C) 2002 Elsevier Inc. All rights reserved.

引用

页码：181 / 191

页数：11