Abstract:
Association rule mining and classification are two important techniques of data mining in knowledge discovery process. Integration of these two techniques is an important research focus and has many applications in data mining. Integration of these two techniques has produced new approaches called Class Association Rule Mining or Associative Classification Technique. These two combined approaches provide better classification accuracy in classifying the data. Content based information retrieval research areas require high efficiency and performance. In these applications association rule mining discovers association patterns from data and based on association patterns we classify target classes. Our paper mainly focuses on combining classification and association rule mining for classifying the data accurately. In this paper we proposed to implement two new algorithms CPAR (Classification Based on Predictive Association Rule) and CMAR (Classification Based on Multiple-class Association Rules) which combines the advantages of both associative classification and traditional rule-based classification. Instead of generating a large number of candidate rules as in associative classification, CPAR adopts a greedy algorithm to generate rules directly from training data. Moreover, CPAR generates and tests more rules than traditional rule-based classifiers to avoid missing important rules. To avoid over fitting, CPAR uses expected accuracy to evaluate each rule and uses the best k rules in prediction. CMAR applies a CR-tree structure to store and retrieve mined association rules efficiently, and prunes rules effectively based on confidence, correlation and database coverage. The classification is performed based on a weighted ?2 analysis using multiple strong association rules. Our extensive experiments show that CMAR is consistent, highly effective at classification of various kinds of databases and has better average classification accuracy in comparison with FOIL (First Order Inductive Learner) and PRM (Predictive Rule Mining). The proposed algorithms are superior in terms of memory requirements, time complexity and eliminate intermediate data structures in implementation.

Keywords: Association Rule Mining, Classification, Data Mining , Knowledge Discovery, FOIL(First Order inductive Learner), PRM(Predictive Rule Mining), CMAR(Classification Based on Multiple-class Association Rules), CPAR(Classification Based on Predictive Association Rule), CBA(Classification Based Association)