Mining Frequent Itemsets using Advanced Partition Approach

Abstract

Frequent itemsets mining plays an important part in many data mining tasks. This technique has been used in numerous practical applications, including market basket analysis. This paper presents mining frequent itemsets in large database of medical sales transaction by using the advanced partition approach. This advanced partition approach executes in two phases. In phase 1, the advanced partition approach logically divides the database into a number of non-overlapping partitions. These partitions are considered one at a time and all local frequent itemsets for those partitions are generated using the apriori method. In phase 2, the advanced partition approach finds the final set of frequent itemsets. The purpose of this paper is to extract the final sets of frequent itemsets from medical retail datasets and to support efficient information used to plan marketing or advertising strategies for medical stores and companies. Algorithms for finding frequent itemsets like Apriori, needs many database scans. But, this advanced partition approach needs to scan the entire database only one time. So, it reduces the time taken for the large database scan in mining frequent itemsets.