文章基本信息

标题：Prevention for Direct and Indirect Discrimination in Data Mining
本地全文：下载
作者：Nikhita B Ugale ; S D Deshpande
期刊名称：International Journal of Computer Science and Information Technologies
电子版ISSN：0975-9646
出版年度：2016
卷号：7
期号：2
页码：960-963
出版社：TechScience Publications
摘要：Data mining helps to extract useful and expectedinformation among the huge amount of collective data presentin database. Automated data collection with data miningcollectively performs automated decisions. Discrimination canbe direct or indirect. Direct discrimination use sensitive datafor decision making. Indirect discrimination makes decisionson the basis of non-sensitive data. For more accuracy theyexpress the relationship between discrimination preventionand privacy preservation in data mining. Along with securityand privacy, proper discrimination performs vital role inconsidering legal as well as ethical point of view of datamining.The main aim behind this paper is to develop newpreprocessing discrimination prevention methodology whichconsist of different types of data transformation methods.With the help of that direct discrimination, indirectdiscrimination or both of them at the same time get prevented.For making the final decision there are two steps in whichfirst step include identification of categories and makes groupsof individuals whatever it may be, directly indirectlydiscriminated for making decision. In second step with thehelp of clustering, transformation of data in specific way suchthat removes all discrimination.
关键词：Direct discrimination ; indirect discrimination;clustering etc.