Boosted Hybrid Privacy Preserving Data Mining (BHPPDM) Technique to Increase Privacy and Accuracy

Abstract

In the current scenario, large volumes of data are generated by different organizations. Data Mining (DM) applications provide suitable patterns that lead to business growth, improved health care and improved services to users etc. The Humongous data volumes may also contain some confidential information about individuals. So, this data may be exploited for identity theft, identity disclosure etc. In this situation, data mining methodologies that provide confidentiality are useful. Though Privacy-Preserving Data Mining (PPDM) methodologies like randomization, perturbation, anonymization etc., provide privacy, but when applied individually, they are ineffective. Henceforth, this article proposes a combination of these techniques called Boosted Hybrid Privacy Preserving Data Mining (BHPPDM). The proposed technique provides more privacy of data than the current methodologies whilst providing better classification accuracy as demonstrated by investigational results.