A Web Data Mining Algorithm Based on Weighted Association Rules

Abstract

Association rules mining is attracting much attention in research community due to its broad applications. Existing web data mining methods suffer the problems that 1) the large number of candidate itemsets, which are hard to be pruned, should be pruned in advance. 2) the time of scanning the database, which are needed to scan transactional database repeatedly, should be reduced. In this paper, a new association rules mining model is introduced for overcoming above two problems. We develop an efficient algorithm-WARDM(Weighted Association Rules Data Mining) for mining the candidate itemsets. The algorithm discusses the generation of candidate-1 itemset, candidate-2 itemset and candidate-k itemset(k>2),which can avoid missing weighted frequent itemsets. And the transactional database are scanned only once and candidate itemsets are pruned twice, which can reduce the amount of candidate itemsets. Theoretical analysis and experimental results show the space and time complexity is relatively good, Meanwhile the algorithm decreases the number of candidate itemsets, enhances the execution efficiency.