Support Vector Machines Parameter Selection Based on Combined Taguchi Method and Staelin Method for E-mail Spam Filtering

Support vector machines (SVM) are a powerful tool for building good spam filtering models. However, the performance of the model depends on parameter selection. Parameter selection of SVM will affect classification performance seriously during training process. In this study, we use combined Taguchi method and Staelin method to optimize the SVM-based E-mail Spam Filtering model and promote spam filtering accuracy. We compare it with other parameters optimization methods, such as grid search. Six real-world mail data sets are selected to demonstrate the effectiveness and feasibility of the method. The results show that our proposed methods can find the effective model with high classification accuracy