ABSTRACT
Advancement in data collection has increased the availability of high-dimensional data. High dimensional data results in data overload which makes the storage and processing complex. Most of the data mining and machine learning algorithms use dimensionality reduction techniques. Dimensionality reduction techniques convert the high -dimensional feature space to low-dimensional feature space to ease the storage and processing of the data. It further enhances the scalability of the machine learning algorithms. In this paper, we discuss various dimensionality reduction techniques used to reduce the feature space.
