基于灰色系统的支持向量回归预测方法

根据部分时间序列数据贫信息、高噪声和非线性等特点，采用含边值修正的灰色模型进行预测，获取残差序列后运用支持向量回归（SVR）方法对模型进行残差修正得到复合的灰色支持向量回归模型．在支持向量回归中构造具有自适用性的动态惩罚参数G替代传统SVR中的不变参数来提高模型的准确性，同时构造算法决定￡以平滑过度调节．广东省工业生产指数的预测试验结果表明，复合模型具有比其他简单模型更理想的预测效果．

SUPPORT VECTOR REGRESSION BASED ON GREY SYSTEM FOR TIME SERIES FORECASTING

The common grey model satisfying with verge value condition was adopted to predict financial time series with some characteristics such as poor information,high noise,non-linearity and so on.Then,the model was revised by support vector regression based on the calculation of the residual error sequence between the predicted values and the original data.Autoadaptive parameters Ci was adopted to replace C in the standard support vector regression to improve the forecasting accuracy.Meanwhile,an algorithm about...