Research and Improvement of Apriori Algorithm for Association Rules

Abstract

With the development and the wide application of DBMS, large-scale database system is popularized in daily life. Data mining is a process of fetching valuable or important information from magnanimous database. Association rules mining is one important research topic of data mining area. Above all most important of all is research on increment association rules mining. In order to renew association rules effectively, the paper introduces the idea of Apriori algorithm; meanwhile it has already analyzed the classic association rule algorithm FUP and IUA, it pointing out its advantages and disadvantages. Finally, it also gives narrative to another improved NIUP and NFUP algorithm. NFUP algorithm joins strong large itemsets into small quantitative of candidate itemsets based on strong large itemsets concept, and adopts early pruning strategy to cut down the times of scanning database.