Variable Selection for Support Vector Machines |
| |
Authors: | Surette Bierman Sarel Steel |
| |
Institution: | 1. Department of Statistics and Actuarial Science , University of Stellenbosch , Matieland , South Africa surette@sun.ac.za;3. Department of Statistics and Actuarial Science , University of Stellenbosch , Matieland , South Africa |
| |
Abstract: | Consider using values of variables X 1, X 2,…, X p to classify entities into one of two classes. Kernel-based procedures such as support vector machines (SVMs) are well suited for this task. In general, the classification accuracy of SVMs can be substantially improved if instead of all p candidate variables, a smaller subset of (say m) variables is used. A new two-step approach to variable selection for SVMs is therefore proposed: best variable subsets of size k = 1,2,…, p are first identified, and then a new data-dependent criterion is used to determine a value for m. The new approach is evaluated in a Monte Carlo simulation study, and on a sample of data sets. |
| |
Keywords: | Kernel model dimension Kernel target alignment Recursive feature elimination Variable selection for SVMs |
|
|