In this study, we propose a new approach that can be used as a kernel-like function for support vector machines (SVMs) in order to get nonlinear classification surfaces. We combined polyhedral conic functions (PCFs) with the SVM method. To get nonlinear classification surfaces, kernel functions are used with SVMs. However, the parameter selection of the kernel function affects the classification accuracy. Generally, in order to get successful classifiers which can predict unknown data accurately, best parameters are explored with the grid search method which is computationally expensive. We solved this problem with the proposed method. There is no need to optimize any parameter in the proposed method. We tested the proposed method on three publicly available datasets. Next, the classification accuracies of the proposed method were compared with the linear, radial basis function (RBF), Pearson universal kernel (PUK), and polynomial kernel SVMs. The results are competitive with those of the other methods.