Comparative study on the Mining Iceberg Cubes Algorithms

Main Article Content

Sheelesh Kumar Sharma
Dr. Pankaj Nagar, Dr. V.P. Gupta


A data warehouse is a collection of data for supporting of decision making process. Data cubes and on-line analytical processing
(OLAP) have become very popular techniques to help users analyze data in a warehouse. An iceberg cube consists of only the set of group-bys
whose aggregates are no less than a user-specified aggregate threshold, and does not compute a complete cube. Mining iceberg cubes is an
important research problem in both online analytic processing (OLAP) and data mining. It can be to answer group-by queries, mine
multidimensional association rules, and identify interesting subsets of the cube for pre-computation. A data warehouse is often organized in a
schema of multiple tables, such as star schema or snowflake schema, in practice. Several algorithms, such as BUC, MultiWay (Y. Zhao et al.,
1997), H-Cubing (Han et al., 2001), and Star-Cubing (Xin et al., 2003), have been proposed to compute iceberg cubes from data warehouse. This
paper focus on comparative study in respect to the performance of all above mentioned algorithms. Researcher finds that MultiWay and HCubing
do not perform well in high dimension and high cardinality datasets. Performance study demonstrates that Star-Cubing is a promising



Keyword: Mining, Algorithms, data warehouse, online analytic processing


Download data is not yet available.

Article Details