Synthesizing multi-dimensional personal data sets

Abstract

This paper presents six different methods to synthesize data sets consisting of personal anonymized multi-dimensional data set. A quick comparative analysis is done at the end. The data is required for various business uses where there is a need to identify the basic individual characteristics of group of persons, without using actual non-sanctioned data from any one real person. In effect there are two useful outcomes – anonymization and data generation for the cases with small data sets.