Abstract:
Association rules can be used to express relationships between items of data. The process of mining associations rules is to analysis the data in a database to discover “interesting” rules. Existing algorithms for mining association rules require that a record in the database contain all the data items in a rule. This requirement makes it difficult to discover certain useful rules in some applications. To solve the problem, this paper describes an algorithm for mining association rules with composite items. The algorithm has the potential to discover rules which cannot be discovered by existing algorithms
