Mining association rules from the star schema on a parallel NCR teradata database system

Author

Chung, Soon M. ; Mangamuri, Murali

Author_Institution

Dept. of Comput. Sci. & Eng., Wright State Univ., Dayton, OH, USA

Volume

1

fYear

2005

fDate

4-6 April 2005

Firstpage

206

Abstract

The Star schema is a popular relational database schema for representing multidimensional data in data warehouses. In this paper, we propose an efficient algorithm, named Star-miner, for mining association rules on the joined result of the tables in the Star schema. The proposed algorithm is designed to be implemented directly on a relational database system by using SQL queries. It is based on the unique properties of the Star schema and does not create the join result of the tables in the schema. We implemented and evaluated the Star-miner on a parallel NCR Teradata database system. The performance of Star-miner is more efficient and scalable than other algorithms which mine the association rules from the single joined table.

Keywords

SQL; data mining; data warehouses; parallel databases; relational databases; SQL queries; Star-miner; association rule mining; data warehouses; multidimensional data; parallel NCR teradata database system; relational database schema; star schema; Association rules; Computer science; Costs; Data engineering; Data mining; Data warehouses; Database systems; Itemsets; Multidimensional systems; Relational databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Information Technology: Coding and Computing, 2005. ITCC 2005. International Conference on

Print_ISBN

0-7695-2315-3

Type

conf

DOI

10.1109/ITCC.2005.195

Filename

1428463