Abstract
Classification rule discovery and association rules mining are two important data mining tasks. Association rules mining discovers all those rules from the training set that satisfies minimum support and confidence threshold while classification rule mining discovers a set of rules for predicting the class of unseen data. In this paper, we proposed a hybrid classification algorithm called ACO-AC, combining the idea of association rules mining and supervised classification using ant colony optimization. It is a class based association rules mining. The proposed technique integrates the classification with the association rule mining to discover high quality rules for improving the performance of classifier. Ant colony optimization is used to mine only the more appropriate subset of class association rules instead of exhaustively searching for all possible rules. First, strong association rules are discovered based on confidence and support and then, these rules are used to classify the unseen data. In proposed approach, we can mine association rules of each class parallel in distributed manner. We compared the proposed approach with eight other state of the art classification algorithms on twenty six data sets. Experiments results show that the hybrid classifier is more accurate and achieves higher accuracy rates when compared with other classification techniques.