Exception rules mining based on negative association rules

Exception rules have been previously defined as rules with low interest and high confidence. In this paper a new approach to mine exception rules will be proposed and evaluated. Interconnection between exception and negative association rules will be considered. Based on the knowledge about negative association rules in the database, the candidate exception rules will be generated. A novel exceptionality measure will be proposed to evaluate the candidate exception rules. The candidate exceptions with high exceptionality will form the final set of exception rules. Algorithms for mining exception rules will be developed and evaluated.