An Effective K-Anonymity Clustering Method for Less Effectiveness on Accuracy of Data Mining Results

Abstract

Data mining technology has interested in means of identifying patterns and trends from large collections of data. It is however evident that the collection and analysis of data that include personal information may violate the privacy of the individuals to whom data refers. The k-anonymity model is one of the most known novel privacy preserving approaches that have been extensively studied for the past few years. In this paper, effective approach that is used the idea of clustering for enforcing the k-anonymity is proposed; the goal of this approach is preserved privacy of data with less effectiveness on data mining results. A set of experiments were carried out on the database of the UC Irvine machine learning repository. The obtained results show that the proposed method keeps data privacy preservation with very low effect on accuracy of data mining results compared with greedy k-member and one pass k-means algorithms.

Keywords: Data mining, privacy preserving data, k-anonymity, greedy k-member, one pass k-means.