Abstract: Apriori algorithm is a classical algorithm using association rules in data mining, The algorithm has the defect of producing a large number of candidate itemsets and scanning the database many times. This paper puts forward an improved Apriori algorithm based on matrix compression, which scans a database and turns it into a Boolean transaction matrix, and then compresses the transaction matrix according to the relevant properties to reduce the amount of computation. The experimental results show that the improved algorithm performance has been significantly improved.

Key words: association rule, Apriori algorithm, transaction matrix, frequent itemsets

摘要： Apriori算法是利用关联规则进行数据挖掘的一种经典算法，但其具有产生大量候选项集和多次扫描数据库的缺点。鉴于此，提出了一种基于压缩矩阵的Apriori改进算法，通过扫描一次数据库，将其转化为布尔事务矩阵，按照相关性质对事务矩阵进行压缩，以减少算法的运算量。实验结果表明，改进算法在性能上得到了明显提高。

关键词: 关联规则, Apriori算法, 事务矩阵, 频繁项集