Towards Reducing the Multidimensionality of OLAP Cubes Using the Evolutionary Algorithms and Factor Analysis

摘要

Data Warehouses are structures with large amount of data collected from heterogeneous sources to beused in a decision support system. Data Warehouses analysis identifies hidden patterns initially unexpectedwhich analysis requires great memory and computation cost. Data reduction methods were proposed tomake this analysis easier. In this paper, we present a hybrid approach based on Genetic Algorithms (GA)as Evolutionary Algorithms and the Multiple Correspondence Analysis (MCA) as Analysis Factor Methodsto conduct this reduction. Our approach identifies reduced subset of dimensions p’ from the initial subset pwhere p' where it is proposed to find the profile fact that is the closest to reference. Gas identify thepossible subsets and the Khi2 formula of the ACM evaluates the quality of each subset. The study is basedon a distance measurement between the reference and n facts profile extracted from the warehouse.