Double Clustering Method in Hiding Association Rules

Association rules are among important techniques in data mining which areused for extracting hidden patterns and knowledge in large volumes of data.Association rules help individuals and organizations take strategic decisions andimprove their business processes. Extracted association rules from a databasecontain important and confidential information that if published, the privacy ofindividuals may be threatened. Therefore, the process of hiding sensitive associationrules should be performed prior to sharing the database. This is done throughchanging the database transactions. These changes must be made in such a way thatall sensitive association rules are hidden and a maximum number of non-sensitiveassociation rules are extractable from the sanitized database. In fact, a balance is tobe established between hiding the sensitive rules and extracting the non-sensitiverules. A new algorithm is presented in this paper to create a balance betweenpreserving privacy and extracting knowledge. The items of sensitive rules areclustered in the proposed algorithm, in order to reduce changes. In fact, reductionof changes and clustering of rules are applied in order to reduce the side effects of the hiding process on non-sensitive rules.

Keywords:

Data Mining , Association Rules , Frequent Item-sets , Privacy Preserving Data Mining Clustering