An Online-Apriori algorithm is proposed to solve the problem that the Apriori algorithm needs to scan the database frequently and update the database in real time when discovering association rules.Through comparative analysis of experiments,it is found that the Online-Apriori algorithm has the following advantages:(1)Compared with the Apriori algorithm,Online-Apriori algorithm scans specific transactions by the number of rows where the newly added frequent 1 itemset is stored in binary bit encoding mode,and reduces the number of scanned transactions when calculating the support.In addition,storing the number of rows in binary bit encoding form saves more memory space than storing the number of rows directly.(2)Compared with the attribute incremental association rule algorithm(ACA+),when there are many candi-date sets,Online-Apriori algorithm greatly reduces the times of pruning judgment,reduces the generation complexity of candidate sets,and greatly shortens the running time.
association rulesOnline-Apriori algorithmbinary bit encodingattribute incremental associ-ation rule algorithm
万方数据
维普
