In this age of information, data is increasing in both number of instances and features. This huge amount of features cause serious problem with respect to learning algorithms and accuracy. Because, in high dimensional data, the number of irrelevant and redundant data might be also huge. So, machine learning algorithms face additional complexity. Unfortunately, as the amount of machine readable information increases, the ability to understand and make use of it does not keep pace with it’s growth. Machine learning provides tools by which large quantities of data can be automatically analyzed. Fundamental to machine learning is feature selection. Feature selection refers to the fact, selecting attributes or variables. In other words, feature selection is an algorithm for finding a optimum subset of feature having minimum classification error or maximum accuracy.