Mining generalized frequent itemsets is one of the most important research areas in data mining. Not only does the taxonomy data widely exist, but the information provided by the generalized frequent itemsets is richer and more valuable than the traditional frequent itemsets. Like traditional mining, the number of generalized frequent itemsets is also very large, which make it difficult to do further analysis. We propose a new method called GIP-summary, which represents the whole frequent generalized itemsets by set profiles; the profiles are used to be more concise.
展开▼
