Title :
Research on the FP Growth Algorithm about Association Rule Mining
Author :
Zhang, Wei ; Liao, Hongzhi ; Zhao, Na
Author_Institution :
Sch. of Software, Yunnan Univ., Kunming, China
Abstract :
For large databases, the research on improving the mining performance and precision is necessary, so many focuses of today on association rule mining are about new mining theories, algorithms and improvement to old methods. Association rules mining is a function of data mining research domain and arise many researchers interest to design a high efficient algorithm to mine association rules from transaction database. Generally all the frequent item sets discovery from the database in the process of association rule mining shares of larger, the price is also spending more. This paper introduces an improved aprior algorithm so called FP-growth algorithm that will help resolve two neck-bottle problems of traditional apriori algorithm and has more efficiency than original one. In theoretic research, An anatomy of two representative arithmetics of the apriori and the FP growth explains the mining process of frequent patterns item set. The constructing method of FP tree structure is provided and how it affects association rule mining is discussed. Experimental results show that the algorithm has higher mining efficiency in execution time, memory usage and CPU utilization than most current ones like apriori.
Keywords :
data mining; transaction processing; very large databases; FP growth algorithm; FP tree structure; aprior algorithm; association rule mining; data mining; frequent item sets discovering; large databases; transaction database; Algorithm design and analysis; Association rules; Data mining; Information management; Relational databases; Seminars; Software algorithms; Software performance; Spatial databases; Transaction databases; Association rule mining; Data mining; FP growth method;
Conference_Titel :
Business and Information Management, 2008. ISBIM '08. International Seminar on
Conference_Location :
Wuhan
Print_ISBN :
978-0-7695-3560-9
DOI :
10.1109/ISBIM.2008.177