摘要： 分析了应用于个性化推荐的Web页面关联规则的特点,提出了“壹支持数下k关联规则”的思想,根据这一思想设计、实现了一种应用于个性化推荐的Web页面关联规则挖掘算法——PARM(Pageview Association Rule Mining)及频繁项集的Freq-Set-Tree存储结构,在产生频繁项的同时挖掘关联规则,因而能提高效率。实验证明在个性化推荐系统中PARM算法的效率明显高于FP-Growth算法。

关键词: 数据挖掘, Web挖掘, 个性化, 关联规则, Freq-Set-Tree

Abstract: The idea of“k association rules on one-support count ” is proposed based on the analysis of characteristics of Web pageview association rules for personalized recommendation. An algorithm of mining association rules for personalized recommendation—— PARM ( pageview association rule mining) and Freq-Set-Tree structure for storing frequent itemsets are designed and implemented according to the idea. The algorithm uses one step for finding frequent itemsets and at the same time mining association rules to improve efficiency. Experiments show that PARM algorithm is more effective in personalized recommendation than FP-Growth algorithm.

中图分类号: 

• TP393