Explanation in OLAP Data Cubes

Explanation in OLAP Data Cubes

Rahhal Errattahi (Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco), Mohammed Fakir (Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco) and Fatima Zahra Salmam (Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco)
Copyright: © 2014 |Pages: 16
DOI: 10.4018/jitr.2014100105

Abstract

OLAP is an important technology that offers a fast and interactive data navigation, it also provides tools to explore data cubes in order to extract interesting information from a multidimensional data structures. However, the OLAP exploration is done manually, without tools that could automatically extract relevant information from the cube. In addition OLAP is not capable of explaining relationships that could exist within data. This paper presents a new approach to coupling between data mining and online analytical processing. Its approach provides the explanation in OLAP data cubes by using the association rules between the inter-dimensional predicates. The mining process could be done by one of the two algorithms, Apriori and Fp-Growth, in which aggregate measures to calculate support and confidence are exploited. It also evaluates the interestingness of mined association rules according to the Lift criteria.
Article Preview

2. General Notations

Let be a data cube with (dimensions, and a non empty set of measures. is the set of hierarchical level belong to the dimension, is the hierarchical level in , For example in the Figure 1 the dimension store contain three hierarchical level: store country, store state and store city.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2019): 1 Released, 3 Forthcoming
Volume 11: 4 Issues (2018)
Volume 10: 4 Issues (2017)
Volume 9: 4 Issues (2016)
Volume 8: 4 Issues (2015)
Volume 7: 4 Issues (2014)
Volume 6: 4 Issues (2013)
Volume 5: 4 Issues (2012)
Volume 4: 4 Issues (2011)
Volume 3: 4 Issues (2010)
Volume 2: 4 Issues (2009)
Volume 1: 4 Issues (2008)
View Complete Journal Contents Listing