Adaptation and Self-Adaptation Mechanisms in Genetic Network Programming for Mining Association Rules

In this paper we propose a method of association rule mining using Genetic Network Programming (GNP) with adaptive and self-adaptive mechanisms of genetic operators in order to improve the performance of association rule extraction systems. GNP is one of the evolutionary methods, whose directed graphs are evolved to find a solution as individuals. Adaptation behavior in GNP is related to adjust the setting of control parameters such as the proportion of crossover and mutation. The aim is not only to find suitable adjustments but to do it efficiently. Regarding to selfadaptation, the algorithm controls the setting of these parameters themselves - embedding them into an individual's genome and evolving them, and it usually changes the structure of the evolution which is typically static. Specifically, self-adaptation of crossover and mutation operators in GNP aiming to change the rate of them by evolution is studied in this paper. Our method based on GNP can measure the significance of the association via the chi-squared test and obtain a sufficient number of important association rules. Extracted association rules are stored in a pool all together through generations and reflected in three genetic operators as acquired information.