Research Of Association Rule Algorithm In Data Mining

Data mining is the knowledge discovery technique oriented to a great deal of data. Association rule is one of the important models of data mining, and has the most significant application value. In the article gave one kind not to need to have the candidate frequent pattern growth algorithm, avoided scanning the database many times, and reduced the time order of complexity. Because the support and the confidence level evaluation criteria have certain limitation, has given a new appraisal threshold value - interest, uses for to prune the senseless rule, thus improved the data mining result quality. And through carries on the expansion to the FP_Growth algorithm, has given highly effective multi-layered connection rule excavation algorithm FP-CH, after the experiment proved that this algorithm is truly effective.