An analysis of association rule mining for classification based on artificial immune system

Abstract

One of the most important and effective data mining techniques is association rule mining. Associative classification uses the principle of rule finding and technique of classification to generate a classifier for prediction. The rule search method is also computationally expensive for small support threshold values, which are critical for designing an efficient classifier. The artificial immune system (AIS) employs the powerful informational capacities of the immune system. The population-based search model combined with evolutionary computation techniques allows the artificial immune system clonal selection methodology to manage a complex search space. This study calculated accuracy across a variety of clonal characteristics and generations to assess the efficacy of the artificial immune system-based categorization method. The output of these systems is shown on several benchmark datasets. Based on the accuracy of the different clonal factors (0.1 to 0.9) and generations (10, 20, 30, 40, 50, and 60), a comparison study is performed. The accuracy is computed using four standard datasets. It is observed that in every dataset for several generations, the approach provides the maximum accuracy with a clonal factor of 0.4.