Implementation Of Data Mining Tools Based On Enterprise Data Warehouse

Data Mining (DM), also named as KDD (Knowledge Discovery in Database) is a hot topic both in research and development, by which we can pick up many trustful, novel, useful and readable patterns from very large amounts of data. It draws upon many techniques from diverse fields, such as database technology, artificial intelligence, machine learning, statistics, fuzzy logic, pattern recognition, and artificial neural network, etc. The combination of Data Mining and Data Warehouse makes Data Mining became an important and relatively independent tool in Data Warehouse.The main contribution of this paper includes:(1) Studies the background of the DW and DM technology's appearance and their development conditions at present.(2) Analyzes the key points of design and implementation DM tools in EDWP. Proposes Apriori-tradeoffAlgorithm;(3) Implements an EDWP-Miner using Visual C++6.0 on Windows 2000, and EDWP-Miner includes the following work: a) Association rules mining, b) Sequential pattern mining, c) Classification rules mining.The thesis is organized as follows:Section 1 introduces the basic concepts and functions of DM and DW. Section 2 analyzes the design of EDWP-Miner in Enterprise Data Warehouse Prototype (EDWP). Section3 introduces the Association rules mining, analyzes the Apriori algorithm, and explains the implementation of Association rules mining in EDWP-Miner in detail. Section 4 gives the basic concepts of Sequential Pattern and GSP algorithm, and then explains the implementation of the Sequential Pattern mining in EDWP-Miner. Section 5 discusses Classification and Decision Tree, and then gives the implementation of the Classification rules mining in EDWP-Miner. In Section 6, a summarization is concluded.