International Journal of Innovative Research in Computer Science & Technology (IJIRCST) ISSN: 2347-5552, Volume-2, Issue-4, July-2014 56 Abstract— The discovery of association rules in data mining is an important issue, the core of which is the frequent pattern mining, Apriori algorithm is traditional for the association rule mining, but it should repetitively scan the database and can produce number of candidates. We present an algorithm of mining hybrid dimension association rules which satisfies the definite condition on the basis of multidimensional transaction database. Boolean Matrix based approach has been employed to generate frequent item sets in multidimensional transaction databases. When using this algorithm first time, it scans the database once and will produce the association rules. Apriori property is used in algorithm to prune the item sets. It is not needed to scan the database again; it uses Boolean logical operations to generate the association rules. It is going to store data in the form of bits, so it needs less memory space. Keywords—Hybrid dimensional association rule, Frequent itemsets, Boolean matrix, multidimensional transaction database. I. INTRODUCTION Finding frequent patterns plays an important role in data mining and knowledge discovery techniques. Association rule describes correlation between data items in large databases or datasets. The first and foremost algorithm to find frequent pattern was presented by R. Agrawal et al.in 1993. Apriori algorithm is expensive to handle a huge number of candidate sets and it requires several scans for the database which is a difficult job. However, in situations with a huge number of frequent patterns, lengthy patterns, or quite little minimum support thresholds, an Apriori-like algorithm may undergo from some above problems and it is used for only single dimensional mining. A. What is Association rule? Association rules are if /then statements that help uncover relationships between seemingly unrelated data in a relational database or other information repository[8].An example of an association rule would be "If a customer buys a toothpaste, he is 80% likely to also purchase toothbrush." An association rule has two parts, an antecedent (if) and a consequent (then). An antecedent is an item found in the data. A subsequent is an item that is found in combination Manuscript received July 22, 2014. Chaitanya B. Pednekar, Computer Engg, Mumbai University/ ACPCE,Kharghar, India. chaitanyap8510@gmail.com R.C.Suryawanshi, Computer Engg, Mumbai University/ ACPCE,Kharghar, India. rakeshsuryawanshi@gmail.com with the antecedent. Association rule is the implication of the form A B, where A and B are item sets which satisfies A I , B I and A∩ B = φ . In data mining, association rules are useful for analyzing and predicting customer activities. They play significant part in shopping basket data analysis, store layout and product clustering. B. Association Rule Mining : in data mining, association rule learning is a popular and well researched method for discovering interesting relations between variables in large databases. It is planned to identify strong rules discovered in databases using different measures of interestingness. For example, the rule ݏݕݑ{ Bread, milk} ⟹ݏݕݑ{ ܤutter} found in the sales data of a supermarket would indicate that if a customer buys bread and milk together, he or she is likely to also buy Butter. Such information can be used as the basis for decisions about marketing activities such as, promotional pricing. In addition to, the above example from market basket analysis association rules are employed today in many application areas including Web usage mining, intrusion detection. As opposite to sequence mining, association rule learning typically does not consider the order of items either within a transaction or across transactions. C. Support and Confidence: In support-confidence framework, each association rule has support and confidence to confirm the validity of the rule. The support denotes the occurrence rate of an itemset in DBT and the confidence denotes the proportion of data items containing B in all items containing A in DBT . ݑ݌( )= ܥouݐ( )/ ܥouݐ( ܤܦ) ݑ݌( ܤ→ܣ)= ݑ݌( ܤ∪ܣ) ݋( ܤ∪ܣ)= ݑ݌( ܤ∪ܣ)/ ݑ݌( ܣ) II. CLASSIFICATION OF ASSOCIATION RULE Association rule can be classified based on dimension appearing in the rule. In multidimensional databases we refer each distinct predicate as a dimension. A. Single dimensional Association Rule: It contain single distinct predicate with multiple occurrences. That means predicate occur more than once in the rule.eg-ݑys( ,"mobile”) ⟹ݏݕݑ( ,"memory card") B. Multidimensional Association rule: A Perspective on Boolean Matrix for Mining Hybrid Dimensional Association Rules Chaitanya B. Pednekar, Prof. R.C.Suryawanshi