Abstract As there are new techniques growing to reveal the hidden information on data, the threat towards those data also increases. Therefore, privacy preservation in data mining is an emerging research area which develops various algorithms to anonymize the data provided for data mining. The existing methodology handles the tradeoff between utility and privacy of data in a more expensive way in terms of execution time. In this paper, a simple Anonymization technique using sub- clustering is specified which achieves maximum privacy and also utility with minimum execution time. The methodology is explained with algorithm and the results are compared with the baseline method. *Author for correspondence Indian Journal of Science and Technology, Vol 7(7), 975-980, July 2014 ISSN (Print) : 0974-6846 ISSN (Online) : 0974-5645 Anonymization by Data Relocation using Sub-clustering for Privacy Preserving Data Mining V. Rajalakshmi 1* and G. S. Anandha Mala 2 1 Sathyabama University, Chennai, Tamil Nadu, India; rajalakshmi.bala03@gmail.com 2 Department of Computer Science and Engineering, St. Joseph’s College of Engineering, Chennai, Tamil Nadu, India; gs.anandhamala@gmail.com 1. Introduction Data are values of qualitative or quantitative variables, belonging to a set of items. In recent years, advances in hardware technology have made an increase in the capa- bility to store and record personal data about consumers and individuals. his has lead to concerns that the per- sonal data may be misused for a various purposes. Data explains a business transaction, a medical record, bank details, educational details etc., Use of technology for data storage and processing has seen an unexpected growth in the last few decades. Such information includes personal details, which the owner doesn’t like to disclose. Such data are the input and sources for data mining. Data mining gives us “facts” that are not obviously seen to human ana- lysts of the data. When such private data are given directly for mining, the security and the privacy of the individual is highly afected. So the data are modiied and provided for data mining. But the problem is that the modiied data should also produce a similar mining result 18, 31 . his has lead to a special research area called privacy preservation in data mining which is an intersection of both data min- ing and information security. he fact in this area is the additional anonymization task which is used to imple- ment the privacy that degrades the performance of the data mining algorithm, which results in incorrect mining results. PPDM techniques can be classiied into two types 5 . (1) Perturbation methods 13 – which alter the data by generalization 17 , suppression, additive or multiplicative factor, fuzzy based, or geometric projections and random number projections. (2) Cryptography based method – they use a public or private key to hide the data and reconstructed when required. Perturbation methods are mainly used with a little compromise on data utility, as the data are altered and or not reversible. Privacy is provided to an extent except closeness attack. For some applications where the data should not be altered at all Keywords: Anonymization, Clustering, Isometric Transformation, Privacy Preservation