Support vector machines (SVM) are becoming increasingly popular for the prediction of a binary dependent variable. SVMs perform very well with respect to competing techniques. Often, the solution of an SVM is obtained by switching to the dual. In this paper, we stick to the primal support vector machine (SVM) problem, study its effective aspects, and propose varieties of convex loss functions such as the standard for SVM with the absolute hinge error as well as the quadratic hinge and the Huber hinge errors. We present an iterative majorization algorithm that minimizes each of the adaptations. In addition, we show that many of the features of an SVM are also obtained by an optimal scaling approach to regression. We illustrate this with an example from the literature and do a comparison of different methods on several empirical data sets.

Additional Metadata
Keywords I-splines, absolute hinge error, huber hinge error, iterative majorization, optimal scaling, quadratic hinge error, support vector machines
Publisher Erasmus School of Economics (ESE)
Persistent URL hdl.handle.net/1765/12011
Citation
Groenen, P.J.F., Nalbantov, G.I., & Bioch, J.C.. (2007). SVM-Maj: a majorization approach to linear support vector machines with different hinge errors (No. EI 2007-49). Report / Econometric Institute, Erasmus University Rotterdam (pp. 1–28). Erasmus School of Economics (ESE). Retrieved from http://hdl.handle.net/1765/12011