Association Rules Candidates To Support The Study Of The Frequency

With the rapid development of information technology, the development of e-commerce and development of WWW popular applications, massive amounts of data have been continuously collected in databases of many application areas, which contain much useful patterns and it is very important to find the hidden and previously unknown information for these areas, and the aims of data mining are to find the above tasks. Association mining is one of the most important study braches, whose aims are to find hidden, interesting and important relations between rules or data. And its results are so simple and easily understood that it has been paid a lot of attention to by more and more scholars, whose study orientations are focused on database, artificial intelligent and statistics. Now a lot of achievement has been adopted by a great few of fields.The algorithm of Apriori is a most standard, popular method for mining associational rules. Its famous property, which is all nonempty subsets of a frequent itemsets must also be a frequent, or if a set cannot pass a test and all of its supersets will fail the same test as well, has been reduction the number of candidate itemsets, but the number of candidate itemsets is still large. Moreover the ratio is so small between frequent itemsets and candidate itemsets that the largest time is wasted in checking the candidate itemsets. A presumptuous guest usurps the host's rule. It's well known that most association algorithms are to find frequent itemsets for associational rules. And the support count of itemsets decides frequent or infrequent. If the support count of itemset is less than the minimum support count, which is supported by users, it is infrequent itemset, or is frequent itemset. To improve the ratio this paper sums up five regularities for Apriori algorithm. At the same time the independent support count is cited to prune the frequent itemsets who are independent their father itemsets. The optimize algorithm has been proved and realized by a few of transaction databases, which proves to reduce the number of candidates and to improve the efficiency of this algorithm.The following is the mainly parts of this paper: firstly it will deeply introduce the contents of data mining especially some technologies of data mining; secondly algorithms of association are introduced and particularly analyzed Apriori algorithm; the last part is the core of this paper, five regularities are particularly discussed by theory and one transaction database realized the algorithm.