Authors : C.M. Velu , M. Ramakrishnan , V. Somu , P. Loganathan and P. Vivekanandan
Abstract: Frequent Item Sets (FIS) play an essential role in many Data Mining (DM) tasks. We want to find interesting patterns from databases (DBs), such as Association Rules (ARs), correlations, classifiers, clusters and many more. The motivation for searching Ars to examine customer�s buying behavior. ARs describe how often items are dependent on each other to purchase together. For example, an AR beer 100% chips 80% states that four of five customers that bought beer also bought chips. Such rules can be useful for decisions concerning product pricing, promotions, store layout and many others. Since their introduction in 1993 by Argawal et al., the FIS and AR mining problems have received a great deal of attention. During the past decade, hundreds of papers have been published to solve these mining problems more efficiently. In this study, we explain the basic FIS and compare various AR algorithms to extract required information from DBs. We describe the main techniques used to solve these problems.
C.M. Velu , M. Ramakrishnan , V. Somu , P. Loganathan and P. Vivekanandan , 2007. Efficient Association Rules for Data Mining. International Journal of Soft Computing, 2: 21-36.