Knowledge-Based Interactive Postmining of Association Rules Using Ontologies

Abstract
In Data Mining, the usefulness of association rules is strongly limited by the huge amount of delivered rules. To overcome this drawback, several methods were proposed in the literature such as itemset concise representations, redundancy reduction, and postprocessing. However, being generally based on statistical information, most of these methods do not guarantee that the extracted rules are interesting for the user. Thus, it is crucial to help the decision maker with an efficient postprocessing step in order to reduce the number of rules. This pro!ect proposes a new interactive approach to prune and filter discovered rules. "irst, we propose to use ontologies #a rigorous and exhaustive organi$ation of some knowledge domain that is usually hierarchical and contains all the relevant entities and their relations%, in order to improve the integration of user knowledge in the postprocessing task. &econd, we propose the 'ule &chema formalism extending the specification language. "or user expectations, "urthermore, an interactive framework is designed to assist the user throughout the analy$ing task. (pplying our new approach over voluminous sets of rules, we were able, by integrating domain expert knowledge in the post processing step, to reduce the number of rules to several do$ens or less. Moreover, the )uality of the filtered rules was validated by the domain expert at various points in the interactive process. Existing S stem (ssociation rule mining is considered as one of the most important tasks in *nowledge Discovery in Databases. (mong sets of items in transaction databases, it aims at discovering implicative tendencies that can be valuable information for the decision maker. These algorithms can discover a prohibitive amount of association rules, for instance, thousands of rules are extracted from a database of several do$ens of attributes and several hundreds of transactions valuable information is often represented by those rare low support and unexpected association rules. If we increase the support for more efficient the algorithms and the discovered rules are obvious. Hence the less they are interesting for the user. (s a result, it is necessary to bring the

support threshold low enough in order to extract valuable information. +nfortunately, the lower the support is, the larger the volume of rules becomes, making it intractable for a decision maker to analy$e the mining result. !isadvantages ,arge amount of data reduce association rules effect. More number of rules represents low support. ,ess interesting rule support low enough in order to extract valuable information.

Pro"osed S stem
In this proposed system different algorithms were introduced to reduce the number of itemsets by generating closed, maximal or optimal itemsets, and several algorithms to reduce the number of rules, using nonredundant rules postprocessing methods can improve the selection of discovered rules. Different complementary postprocessing methods may be used, like pruning, summari$ing, grouping, or visuali$ation. -ew interactive postprocessing approach, ('I.&/ #(ssociation 'ule Interactive post .rocessing using &chemas and /ntologies% to filter discovered rules. "irst, we propose to use Domain /ntologies in order to strengthen the integration of user knowledge in the postprocessing task. &econd, we introduce 'ule &chema formalism by extending the specification language for user beliefs and expectations toward the use of ontology concepts. "urthermore, an interactive and iterative framework is designed to assist the user throughout the analy$ing task. The interactivity of our approach relies on a set of rule mining operators defined over the 'ule &chemas in order to describe the actions that the user can perform. Advantages &election of discovered rules like domain ontologies, rule schema formalism. Integration of user knowledge in postprocessing. Interactive framework is designed for analysing tasks.

Software Re#uirements
0 0 0 /perating system "ront 6nd =ackend 1 2indows 3.45. 1 7isual &tudio 899:, .-et, ;<. 1 &>, &erver 899?.

$ardware Re#uirements
0 0 0 .rocessor Hard disk '(M 1 .entium I7. 1 :9 @=. 1 ?A8 M=.