Optimizing area under the Roc curve using genetic algorithm

Class imbalance is one of the main obstacles in data mining. AUC is one of the main criterions to judge the performance of classifiers, which have been applied in class imbalanced datasets. So, optimizing AUC method has been realized by using gradient method to optimize it directly. But optimizing AUC method limits the shortcoming of gradient method, which is generally converged in local minima. So, this paper introduced the genetic algorithm into optimizing AUC method, and compared it with the previous one. The results of the experiment proving the method in this paper is more suitable for imbalanced datasets than the previous one.