An Assembly of Discrimination Prevention Techniques in Data Mining
Anuja C. Tikole1, Vikash V. Kamle2, Shekhar J. Jadhav3, Aditya S. More4, Asmita Mali5
1Anuja C. Tikole, Department of Information Technology, Pd. Dr. D. Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India.
2Vikash V. Kamle, Department of Information Technology, Pd. Dr. D. Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India.
3Shekhar J. Jadhav, Department of Information Technology, Pd. Dr. D. Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India.
4Aditya S. More, Department of Information Technology, Pd. Dr. D. Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India.
5Prof. Asmita Mali, Department of Information Technology, Pd. Dr. D. Y. Patil Institute of Engineering and Technology, Pimpri, Pune, India.
Manuscript received on March 05, 2015. | Revised Manuscript received on March 22, 2015. | Manuscript published on April 30, 2015. | PP: 8-12 | Volume-4 Issue-4, April 2015. | Retrieval Number: D3816044415/2013©BEIESP
Open Access | Ethics and Policies | Cite
© 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 the extraction of implicit, previously unknown, and potentially useful information from available data. The idea is to make computer programs that come through databases automatically, seeking regularities or patterns. In data mining, the data is stored electronically and search is automated by computer. Data mining is about solving problems by analyzing data already present in databases. There are, however, negative social perceptions about data mining, among which unjustifiable access and potential discrimination. Discrimination consists of unfairly treating people on the basis of their belonging to a particular group. Automated data collection and data mining techniques such as classification rule mining gives the way to making automated decisions, for e.g., loan granting/denial, insurance premium computation, etc. If the training data sets are biased in what regards discriminatory (sensitive) attributes as gender, race, religion, etc., discriminatory decisions may happen. Due to this, antidiscrimination techniques including discrimination discovery and prevention have been introduced in data mining .Discrimination is a presuppose privileges where provide to the each separate group for the safety of the data which is stored . Discrimination can be either direct or indirect. Direct discrimination finds when decisions are made based on sensitive attributes. Indirect discrimination occurs when decisions are made based on non-sensitive attributes which are strongly correlated with biased sensitive ones. In this paper, proposed system covers discrimination prevention in data mining and propose new techniques applicable for direct and indirect discrimination prevention both at the same time.
Keywords: Data mining, Direct and Indirect Discrimination prevention, Antidiscrimination.