An applied research based on improved association rules

Apriori algorithm usually generates a lot of candidate sets in data mining, and needs to repeatedly scan all the data of the database. Making it in the implementation process efficiency is greatly reduced. This paper proposes the establishment of a number of linear lists recording each transaction in order to achieve the purpose of reducing transaction. Setting value of `up´ to raise the threshold of combination of frequent 1-itemsets. It finds 2-item candidate for setting to achieve the purpose of pruning. The experimental results show that the improved algorithm performance has been significantly improved.