金融时间序列预测中的GA-SVR方法

针对支持向量机方法在金融时间序列预测的过程中,模型参数选取不当的导致预测精度较低等问题,利用遗传算法优化选取支持向量机模型参数,建立了一种基于遗传算法优化支持向量机参数的金融时间序列预测模型。并将该方法应用于我国上证指数时间序列预测中。实验结果表明基于遗传算法优化的支持向量机方法能较好的反映金融时间序列预测规律,并且提高了模型预测精度。

The Application of GA-SVR Method in Financial Time Series Prediction

The application of support vector machine method in financial time series forecasting process often occurred low prediction accuracy and other issues with selected model improper parameters.In order to solve the problems,a financial time series forecasting model based on Genetic Algorithm which is used to optimize parameters of SVM has established.It was applied in China ＇stock index time series prediction,and experimental results show that the method could better reflect the financial time series prediction rule,and improved the prediction accuracy of the model.