Extracting Knowledge in Data Warehouses using Fuzzy AprioriTid

Abstract

Multidimensional databases and OLAP tools that provide an efficient framework for data mining have been pushing us to the OLAM architecture. OLAP is widely used to illustrate meaningful and interactive analysis of data on the complex structure. In contrast, detecting hidden patterns in the data and exploring them is for the data mining. OLAP and data mining are believed to complete each other for analyzing large data sets in decision support systems efficiently. Unlike previous work in this field, this method does not rely on the availability of knowledge in a particular field. Variables will be selected with the consideration of user to build cubes. Hierarchical clustering is used to obtain dynamic relationships between variables at different levels of data. Results of the Adult data set shows that the obtained Lift from Fuzzy AprioriTid compared with Apriori algorithm increased.