Cluster based data reduction method for transaction datasets

The common feature of transaction datasets is that it is very huge in size, so it is important to develop a technique for dataset reduction. The process of dataset reduction must not change the features of the original dataset; this will increase the effectiveness and efficiency of extracting association rules from these datasets without affecting the original data. Disjoint clusters that have different number of transactions will be introduced in order to minimize the search space, this in turn will decrease the time required to mine the desired rules by dealing with each cluster individually. The support and confidence measures will be used to determine the frequent item sets and exclude the others.