Journal of Theoretical and Applied Information Technology
Data mining services require accurate input data for their results to be meaningful, but privacy concerns may influence users to provide spurious information. In this paper, the authors have presented an efficient algorithm for mining of privacy preserving high utility item sets by considering the sensitive item sets. The algorithm comprise of three major steps to attain the aim of their research includes: data sanitization, construction of sensitive utility FP-tree and mining of sensitive utility item sets. The experimentation has carried out using real as well as the synthetic dataset and the performance of the proposed algorithm is evaluated with the aid of the evaluation metrics such as Miss cost and Database difference ratio.