一种基于FP树的挖掘关联规则的增量更新算法

挖掘关联规则是数据挖掘领域的一个重要研究方向．人们已经提出了许多用于高效地发现大规模数据库中关联规则的算法，但对关联规则维护问题的研究却比较少．该文在FP树的基础上，引入支持度函数的慨念，对FP树进行改造，提出了一种关于挖掘关联规则的增量更新算法IFP—growth．该算法既考虑了数据集中数据的增加．同时又考虑了数据集中数据的减少等情况下关联规则的维护问题，并且还可以把增量更新的5种情形简化为3种情形．使用本算法来挖掘关联规则可以避免生成大量的候选项目集，而且非常高效．

A FP-Tree Based Incremental Updating Algorithm for Mining Association Rules

Association rules mining is an important research topic in data mining area, which has been successfully applied to commercial domains. For this reason, many approaches have been proposed to mine association rules, but little work was done on their maintenance. This paper puts forward an incremental updating algorithm on the basis of FP-tree. Firstly the concept of support function is introduced. Then an incremental updating model is presented, which contains the construction of IFP-tree and IFP-tree growth algorithm. The model considers not only adding new data into the database but also reducing old data from the database. Furthermore, it can predigest five cases to three cases. Finally, some nontrivial experiments have been conducted. The results show that IFP-growth algorithm is powerful and efficient, suitable for mining association rules, as well as for some other purposes. Additionally, a small example is presented to illustrate how to define the support function Z and how to develop IFP-tree.