Abstract: Traditional studies of frectuent itemset mining cannot obtain information from uncertain data efficiently. We studied the frequent pattern tree and proposed an effective uncertain data preconditioning method, the PCAFP-Growth, which can reduce the itemset dimensions with principal component analysis method,and prune data with fuzzy associa- lion analysis. Our experimental results over real world datasets show that our method is effective and efficient

Key words: Uncertain data, Frequent itemset, Principle component analysis, Fuzzy association