Published Paper Details:

privacy preserving data mining, anonymization based approaches have been utilized to safeguard the privacy of a person. Existing writing tends to different anonymization based approaches for preserving the delicate private data of a person. The k-namelessness model is one of the broadly utilized anonymization based approach. Be that as it may, the anonymization based approaches experience the ill effects of the issue of data misfortune. To limit the data misfortune different best in class anonymization based clustering approaches viz. Ravenous k-part calculation and Systematic clustering calculation have been proposed. Among them, the Systematic clustering calculation gives lesser data misfortune. Furthermore, these approaches utilize all characteristics during the making of an anonym zed database. Along these lines, the danger of exposure of delicate private data is higher through distribution of the considerable number of traits. In this paper, we propose two approaches for limiting the revelation hazard and preserving the privacy by utilizing deliberate clustering calculation. First approach makes an inconsistent mix of semi identifier and touchy property. Second approach makes an equivalent mix of semi identifier and touchy property. We likewise assess our approach exactly concentrating on the data misfortune and execution time as essential measurements.