New coding method to reduce the database size and algorithm with significant efficiency in association rules

The problem of discovery association rules in large databases is considered. An encoding method for converting large databases to small one is proposed. Significant efficiency is obtained by applying some modified known algorithm on our proposed database layout. In addition, a new algorithm based on the proposed encoding method is introduced. Using some properties of numbers our database converts itemset to numerical domain. Our implementation indicates that the proposed layout made the size of database significantly smaller. Also the time to find association rules is reduced.