Association Rule Mining with Establishment of Frequent Item Set Vectors

After analyzing many typical association rule mining algorithms, a new algorithm, named as BOFP-V, is proposed for frequent item set mining. FP-V vectors are introduced in order to convert that of frequent item set mining to the course of the vectors operating. The existing Apriori algorithm produces a lot of candidacy sets and needs scanning database many times, and BOM algorithm entails and operation of k vertors with (_m^k) times. Overcoming these drawbacks, BOFP-V algorithm needs scanning database only once. Therefore, the proposed algorithm is obviously superior to Apriori and BOM algorithm in efficiency.