【摘要】 针对频繁项集挖掘时间与空间效率低的问题,提出一种基于New FP-tree的高效频繁项集挖掘算法。此算法利用New FP-tree结构存储事务数据库中的频繁项集信息,无需递归构造条件模式树,仅需两次扫描数据库即可生成所有频繁项集。最后的实验证明了该算法的有效性。更多还原

【Abstract】 Aiming at the problem of low time and space efficiencies for frequent item set mining, an algorithm for frequent item set mining based on New FP-tree is proposed. The algorithm constructs New FP-tree to compress business database. Without recursion condition pattern tree, the algorithm needs to scan database only two times to produce all frequent item set. Lastly the algorithm is realized on experiment and is proved to be valid.更多还原