A Privacy Data Protection Algorithm for Mining Association Rules
For resolving the problem that the existing protection methods of privacy data in association rule mining likely to affect the usability and validity of the result of the data mining, a new privacy data protection algorithm called APPDARM, which is based on data exchange technology, is put forward. At the same time, the corresponding data exchange method is available. The proposed method could effectively protect the privacy data, maximum keep the association rules of the original data, and most importantly, do not produce ghost rules. Simulation test results show that APPDARM algorithm has a better privacy and accuracy.