Machine Learning for Classification of Imbalanced Big Data

Abstract

The problem of classification of imbalanced datasets is a critical one. With an increase in the number of application domains that rely on classification, extensive research has been carried out in this field; with focus directed towards the problem of poor classification accuracy. Of late, the rise in significance of Big Data has forced industries to search for better techniques to handle massive and unstructured datasets; this has led to a need for robust classification algorithms that deal with unbalanced Big Data. This paper surveys the current algorithms provided by Machine Learning for unbalanced dataset classification and considers their possible use for larger or unstructured datasets.