Transaction Association Rules Mining

The world has entered the ear of information, there are a great deal of data in all sorts of fields,It is very urgent for people to transform them into useful information and knowledge,and apply them in business administration, production control and forecasting, ect. As a kind of technology for extracting information from large quantity of data. Data Mining and knowledge discovery has become a significant research problem which has important theoretical and practica ues, and attracts widely attention in intermational academe, upon investigating into the research achievements and disadvantages of existing in knowledge discovery in database and in dataminingothis thesis advanced the research and application of mining the inter-transactional association rules. Improving and Compareing FITI with EH-Apriori.First,the development survey is shown about data mining technology and the concept about association rule mining described by the numbers. Because association mining has developed rapidly in these several decades. Ithas been extended to other and we also analyze this instance at large. The rule of association mining is introduced including a few of main algorithms.Second, introduction EH-Apriori algorithm, using traditional Apriori algorithm to discover frequent intertransaction itemsets. To enhance the efficiency further, a hashing technique is used, when the support of candidate intertransaction one-itemsets is counted by scanning the database, information about candidate intertransaction two-itemsets is collected in advance in such a way that all the possible two-itemsets are hashed to a hash table. Each bucket in the hash table consists of a number to represent how many itemsets have been hashed to this bucket so far. The hash table is then used to reduce the number of candidate intertransaction two-itemsets. This is done by removing a candidate two-itemsetsif its corresponding bucket value in the hash tablelis less than minsup. we call the Extended Hash Apriori or EH- Apriori.Last, introduction detailed the notion of intertransaction association rule: in this study, Break the barrier of transactions and extend the scope of mining associationrules from traditionasingle-dimensional, intratransaction associations to multidimensional, intertransaction associations. An intertransaction association describes the association relationships among different transaction, the associated items belong to differenttransactions. Moreover, such an intertransaction association can be extended to associate multiples in the same rule, so that multidimensional intertransaction associations can also be defined and discovered. Mining intertransaction associations pose more challenges on efficient processing than mining intratransaction associations because the number of potential association rule becomes extremely large after the boundary of transactions is broken, in this study, Introduce the notion of intertransaction association rule, define its measurements:support and confidence, and develop an efficient algorithm, FITI(an acronym for"First Intra Then Inter"), for mining intertransaction associations,which adopts two major ideas:l)an intertransaction frequent itemset contains only the frequent itemsets of its corresponding intratransaction counterpart;and 2)a special data structure is built among intratransaction frequent itemsets for efficient mining of intertransaction frequent itemsets. Compare FITI with EH-Apriori,further extensions of the method and its implications are also discussed in the paper.