Data Reduction Techniques: A Comparative Study

Abstract

Data preprocessing in general and data reduction in specific represent the main steps in data mining techniques and algorithms since data in real world due to its vastness, the analysis will take a long time to complete .Almost all mining techniques including classification, clustering, association and others have high time and space complexities due to the huge amount of data and the algorithm behavior itself. That is the reason why data reduction represent an important phase in Knowledge Discovery in Databases (KDD) process. Many researchers introduced important solutions in this field. The study in this paper represents a comparative study for about 22 research papers in data reduction fields that covers different data reduction techniques such as dimensionality reduction, numerisoty reduction, sampling, clustering data cube aggregation and other techniques. From the conducted study, it can be concluded that the appropriate technique that can be used in data reduction is highly dependent on the data type, the dataset size, the application goal, the availability of noise and outliers and the compromise between the reduced data and the knowledge required from the analysis