SYNTHETIC MICRODATA GENERATION IN PRIVACY PRESERVING DATA MINING

Abstract

Data mining is the process of extracting the previously unknown patterns from large amount of data. Privacy preserving data mining is one of the reserve areas in data mining. It is used to provide the privacy for personally identifiable information in data mining. It also provides security to protect data. Privacy preserving Association Rule Mining, Privacy Preserving Clustering, Privacy Preserving classification, and etc., are some of the privacy preserving algorithms. The various techniques used in the privacy preserving data mining are statistical disclosure control, randomization, k-anonymity and I-diversity. In this paper, we havediscussed about the synthetic data generation concept, its techniques and methods which are used for protecting sensitive data in statistical disclosure control.