A New Perfect Hashing and Pruning Algorithm for Mining Association Rule

Hassan Najadat1, Amani Shatnawi2 and Ghadeer Obiedat2

1Computer Information Systems Department, Jordan University of Science and Technology, Irbid, Jordan
 
2Computer Science Department, Jordan University of Science and Technology, Irbid, Jordan

Copyright © 2011 Hassan Najadat, Shatnawi Amani and Obiedat Ghadeer .This is an open access article distributed under the Creative Commons Attribution License unported 3.0, which permits unrestricted use, distribution, and reproduction in any medium, provided that original work is properly cited.

Abstract

This paper presents a new hashing algorithm in discovering association rules among large data itemsets. Our approach scans the database once utilizing an enhanced version of priori algorithm, Direct Hashing and Pruning algorithm (DHP). The algorithm computes the frequency of each k itemsets and discovers set of rules from frequent k itemsets. Once the expert in the application domain provides the minimum support, the pruning phase is utilized to minimize the number of k itemsets generated after completing the scanning of specific size database.  The required data structure is built to implement the hash table.  The analysis shows that the new algorithm does not suffer from the collisions, which lead to high accuracy.

Keywords: Association Rule Mining, Direct Hashing, Basket Market Analysis.
Shares