A Growing Evolutionary Algorithm for Data Mining

An unsuitable representation will make the task of mining class association rules very hard for a traditional genetic algorithm (GA). But for a given dataset, it is difficult to decide which one is the best representation used in the mining progress. In this paper, we analyses the effects of different representations for a traditional GA and proposed a growing evolutionary algorithm which was robust for mining class association rules in different datasets. Experiments showed that the proposed algorithm is effective in dealing with problems of deception, epistasis and multimodality in the mining task.