分类规则挖掘算法研究与应用

he paper presents an algorithm MSC of multi-support classification, which adopts the frequent classification item-set tree to organize the frequent pattern sets, and array to figure the classification projected transaction subsets, and applies multiple supports for classification rules mining. The MSC uses the breath first strategy assisted by the depth first strategy, and adopts pseudo projection, which makes it unnecessary to scan the database and construct the projected transaction subsets repeatedly. This reduces the memory and time cost, and makes it more projecting-efficient and scalable. The MSC algorithm can be used in the basket analysis, consumption behavior and the association rules mining in the retailing industry, which support the product layout, buying recommendation and the efficiency of sales promotion.