Machine Leing (ML) techniques have been widely applied in recent traffic clas-sification. However, the problems of both dis-criminator bias and class imbalance decrease the accuracies of ML based traffic classifier. In this paper, we propose an accurate and exten-sible traffic classifier. Specifically, to address the discriminator bias issue, our classifier is built by making an optimal cascade of binary sub-classifiers, where each binary sub-classi-fier is trained independently with the discrimi-nators used for identifying application specific traffic. Moreover, to balance a training dataset, we apply SMOTE algorithm in generating artificial training samples for minority classes. We evaluate our classifier on two datasets col-lected from different network border routers. Compared with the previous multi-class traffic classifiers built in one-time training process, our classifier achieves much higher F-Measure and AUC for each application.