Association rules is a very important part of data mining. It is used to findthe interesting patterns from transaction databases. Apriori algorithm is oneof the most classical algorithms of association rules, but it has thebottleneck in efficiency. In this article, we proposed a prefixed-itemset-baseddata structure for candidate itemset generation, with the help of the structurewe managed to improve the efficiency of the classical Apriori algorithm.
展开▼