期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：2
DOI：10.15680/ijircce.2015.0302081
出版社：S&S Publications
摘要：Frequent item set mining is one of the most popular field and most common field of data mining. At thesame time, it is a very complex and a time consuming process. Although there are many algorithms are available tomine the frequent patterns from a voluminous data set, but there is still a lot of scope to mine frequent data fromdifferent data sets in less time & in less memory. Frequent pattern mining is very useful in cross marketing, marketbasket analysis, credit card fraud detection. Knowledge discovery in databases (KDD) helps to identifying preciousinformation in such huge databases. This information helps the decision makers in making decision. Ultimately thistype of information helps in various goals like – sales increase, profit maximization, prediction etc. In this paper, wehave proposed a novel compact data structure based method to discover frequent pattern mining. The proposed methodtransforms the original data set into a transformed and compacted data set & then it discovers the frequent patternsfrom the transformed data set.
关键词：Data Mining; Association Rule; Support; Confidence; Frequent Item-sets
