AbstractThe apriori scans database many times and generates large candidate itemsets so that its I/O performance and efficiency seriously affect the universal application and promotion. In order to solve the problem, the paper proposed a method by seting a unique number and recording the location of each itemset. It scans the database once and never generates the huge candidate itemsets and has been applied to QAR data. Experiments show that the proposed algorithm is capable of discovering meaningful and useful association rules in an effective manner, speeding up less execution time.