Improving the Performance of Association Rules Hiding using Hybrid Optimization Algorithm

Abstract

In this digital world, information evolves from several sources like social media, e-commerce sites, and mobile networks, etc., in large volumes for processing. The sensitiveness in the form of rules extracted from different resources entails that privacy-preserving is a significant research issue to be cared for. In this context, it is imperative to impose confidentiality on sensitive rule data during its processing. Optimization algorithms play a vital role in the reduction of ghost rules and lost rules in association rule hiding. This paper proposes a novel Hybrid optimization algorithm that acquires the characteristics of the above-said algorithms for association rule hiding and it has been shown that it produces better results in less time. Further, the newly introduced concepts on the lost rule generation and recovery are seen to produce almost 99% of lost rules with a reduction in side effect factors from 24–5%.