Abstract | ||
---|---|---|
In this paper, we analyze some potential problems in the existing mining algorithms on association rules. These problems are caused by only concerning about its support and confidence, while neglecting to what extent the rule will interest people. At the same time, the existing definition and mining algorithms of association rules does not take into account any negative items, therefore many valuable rules are lost. We hereby introduce the concepts of interest measure and negative item into the definition and evaluation system. Then we modify the existing algorithms so as to use interest measure to generate rules with negative items. At the end of this paper we analyze the new algorithm and prove it to be efficient and feasible. |
Year | Venue | Keywords |
---|---|---|
2000 | Web-Age Information Management | negative items,existing algorithm,negative item,evaluation system,interest measure,mining algorithm,potential problem,existing mining algorithm,existing definition,mining association rules,new algorithm,association rule |
Field | DocType | Volume |
Data mining,Evaluation system,Computer science,Association rule learning,Artificial intelligence,Knowledge extraction,Data mining algorithm,Machine learning | Conference | 1846 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-67627-9 | 2 |
PageRank | References | Authors |
0.39 | 4 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haofeng Zhou | 1 | 86 | 7.22 |
Pan Gao | 2 | 12 | 3.62 |
Yangyong Zhu | 3 | 243 | 31.66 |