Mining Generalized Multiple-level Association Rules

Abstract

Mining association rules is an important task for knowledge discovery. We can analyze past transaction data to discover customer behaviors such that the quality of business decision can be improved. The strategy of mining association rules focuses on discovering large itemsets which are groups of items which appear together in a sufficient number of transactions. In this paper, we propose a graph-based approach to generate generalized multiple-level association rules from a large database of customer transactions, which describes the associations among items in any concept level. This approach is to scan the database once to construct an association graph, and then traverse the graph to generate large itemsets.