支持向量机(support vector machine,简称SVM)是一种基于结构风险最小化原理的分类技术,也是一种新的具有很好泛化性能的回归方法.提出了一种将回归问题转化为分类问题的新思想.这种方法具有一定的理论依据,与SVM回归算法相比,其优化问题几何意义清楚明确. Support vector machine (SVM) is a classification technique based on the principle of structural risk minimization and a new regression method with good generalization performance. A method is proposed to convert the regression problem into a classification problem This method has certain theoretical basis, compared with the SVM regression algorithm, the geometry of the optimization problem is clear and definite.