Privacy Preserving Features Selection for Data Mining using Machine Learning Algorithms

Features selection known as process of lessening the number of inputs while designing a predictive model using machine learning algorithms. Metadata is an asset because useful information is concealing in these large quantities of data. Data analytics needs more in-depth insight and the identification of fine-grain patterns to make precise predictions that allow better decision-making. To make identification towards the data, the privacy of the data must be preserving. It will ensure there is no leakage information to other parties. In this paper, we review features selection for data mining and machine learning algorithms to preserve data privacy.