THE SCALABLE REVERSIBLE RANDOMIZATION ALGORITHM (SRRA) FOR BETTER PRIVACY PRESERVATION, IMPROVED FEATURE SELECTION STABILITY, AND HIGHER ACCURACY IN BIG DATA ANALYTICS

In today’s knowledge economy, every organization uses the enormous accumulated data for their development of business as well as for enhancing customer relationship management. However, most of the data produced is unstructured and semi-structured and comprises customers' private data. Data analysis is mostly done by a third party to get insights and hidden patterns or information. Preserving the individual’s privacy is vital for organizations before analysing it for pattern mining. Because of the proliferation of electronic gadgets and technological progressions, the dimension of the collected dataset increases into the high dimensional dataset. This will lead to feature selection, which is a vital preprocessing step for big data analytics as a dimensionality reduction technique. Previously, researchers believed that the stability of feature selection depends generally on the algorithm but recently confirmed by scientists it depends on the dataset’s statistical characteristics. Unstable feature selection results confuse researchers' minds about their research conclusions as the selection stability positively correlated with accuracy. Privacy preservation will disturb the statistical characteristics of a dataset, which will impact the stability of feature selection and accuracy. Hence, privacy conserving big data analytics techniques should protect the sensitive data of individuals with better stability of feature selection and accuracy. The research paper evaluates the methods of privacy conserving big data analytics and recommends a new reversible privacy conserving algorithm called Scalable Reversible Randomization Algorithm (SRRA)