An Enhanced Approach for Privacy Preservation in Anti-Discrimination Techniques of Data Mining
Sreejith S.1, Sujitha S.2

1Sreejith S., Department of Computer Science & Engineering, L B S Institute of Technology for Women, Thiruvananthapuram (Kerala), India.
2Sujitha S., Department of Computer Science & Engineering, L B S Institute of Technology for Women, Thiruvananthapuram (Kerala), India.

Manuscript received on 15 August 2015 | Revised Manuscript received on 25 August 2015 | Manuscript Published on 30 August 2015 | PP: 299-308 | Volume-4 Issue-6, August 2015 | Retrieval Number: F4248084615/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Data mining is an important area for extracting useful information from large collections of data. There are mainly two threats for individuals whose information is published: privacy and discrimination. Privacy invasion occurs when the values of published sensitive attributes is linked to specific individuals. Discrimination is the unfair or unequal treatment of people based on their membership to a specific category, group or minority. In data mining, decision models are mainly derived on the basis of records stored by means of various data mining methods. But there may be a risk that the extracted knowledge may impose discrimination. Many organizations collect a lot of data also for decision making. The sensitive information of the individual whom the published data relate to, may be revealed, if the data owner publishes the data directly. Hence, discrimination prevention and privacy preservation need to be ensured simultaneously in the decision making process. In this paper, discrimination prevention along with different privacy protection techniques have been proposed and the utility measures have been evaluated.
Keywords: Discriminatory Attribute, Direct Discrimination Prevention, Indirect Discrimination Prevention, Rule Generalization, Rule Protection, K-Anonymity, L- Diversity, T-Closeness

Scope of the Article: Data Mining