A novel mining Method of Global Negative Association Rules in Multi-Database

Mining Negative Association Rules in multi-database has attracted more and more attention. Most existing research focuses on unifying all negative rules discovered from different single databases into a single view. This paper presents a novel method for mining global negative association rules in multi-database. This method produces some infrequent itemsets of potential interest by scanning constructed Multi-Database Frequent Pattern tree, and extracts negative association rules of interest according to the proposed correlation model from multi-database. Experimental results show the effectiveness and efficiency of the proposed algorithm.