A Survey to Identify a Suitable Clustering Algorithm for Estimating the Efficiency of Privacy Preserving Data Mining Techniques

With the current advancement in information technology we have data warehouses containing abundant data which results in a new dimension of research in data mining arena known as Privacy Preserving Data Mining (PPDM). Many algorithms have been proposed incorporating a privacy mechanism that allows the users to extract the required information without revealing the sensitive data. The efficiency of privacy preserving algorithm is computed using a privacy metric known as misclassification error. The prime objective of this paper is to analyze various clustering algorithms and to identify the one with the minimum misclassification error.