The Application of Support Vector Machine Improved Method In Analyzing Macroeconomic

This article presents a new SVM (support vector machine) fast learning algorithm which is based on the boundary vector. The speed of this algorithm has been improved considerably than traditional support vector machine,the requirement of memory space has also been obviously reduced. At the same time,because the support vector won´t be lost in the process of selecting the boundary vector, So the performance of SVM will not be affected. Based on an instance which proves that this method can achieve the desired results when it is applied to the classification of macroeconomic forecasting.