Association Rules Algorithm And Its Application

With the deepening of the application of database, the size of database expands quickly, people need to analyse these data and find the worthy informations. But the database management systems do not provide available tools to analyse and use these data, so data mining appears and becomes the hotspot. People pay much attention to Association rules in data mining. It finds the relations between itemsets among historical data and pick up useful and interesting models. This thesis researchs association rules by the numbers.The author summarizes the researching actuality and the production of application, then analyses the standard theories and the measure of sorting. The thesis analyses the classic Apriori algorithm, and provides the measure of scaling the value of association rules. At the base of analysis of theories, we analyse the algorithm of multi-Dimensional association rules and sequence pattern. We provide the improving algorithms after we analyse the standard theories and algorithms about them. They are multi-dimensional association rule algorithm based on vertical data layout and Equivalence Class Clustering, sequence pattern algorithm with constraint of time. The improving algorithms have better efficiency than original ones and can adapt on the user's special demands in actual application of data mining.Later, the author puts the improving multi-demensional association rule algorithm into the analysis of the losing customers in mobile telecommunication corporation. The thesis analyses the design of flow, selection of data and concrete apply of the mining in the data of characters of customers. At last, we analyse the mined rules and give the advices of improving the model.