约束关联挖掘是在把项或项集限制在用户给定的某一条件或多个条件下的关联挖掘,是一种重要的关联挖掘类型,在现实中有着不少的应用。但由于大多数算法处理的约束条件类型单一,提出一种多约束关联挖掘算法。该算法以FP-growth为基础,创建项集的条件数据库。利用非单调性和单调性约束的性质,采用多种剪枝策略,快速寻找约束点。实验证明,该算法能有效地挖掘多约束条件下的关联规则,且可扩展性能很好。
Association rules mining with constraints is an important association mining method.It can mine the rules according to the given itemsets constraints.Because most of algorithms can only deal with single type of constraints,this paper proposed an efficient algorithm for mining association rules with multiple constraints.The algorithm was based on FP-growth algorithm,and generated the condition database of frequent itemsets.Making use of constraint characteristics of anti-monotone and monotone,moreover,using some prune techniques,to find the constraint checking points,the proposed algorithm was efficient for mining association rules with multiple constraints.Experimental results show that the proposed algorithm is efficient both in running time and scalability.