基于PP-BPNN的黄金价格预测模型

Gold Price Forecasting Model Based on Projection Pursuit and Neural Network

黄金价格受到多种因素影响,是一个复杂的非线性态系统,按传统线性规律建模预测,误差较大。为了提高黄金价格预测精度,提出一种投影寻踪和神经网络相结合的黄金价格预测模型。首先利用投影寻踪算法对影响因子进行筛选,降低特征空间的维数然后根据选择的影响因子对黄金价格样本进行处理,并输入到BP神经网络进行学习,建立黄金价格预测模型,最后通过实验对模型预测性能进行测试。实验结果证明,组合模型能够很好刻画黄金价格变化趋势,简化神经网络结构,加快收敛速度,进一步提高了黄金价格的预测精度和运行效率。

In order to improve the precision of gold price forecastint,this paper proposed a gold price combination forecasting model based on pursuit algorithm and neural network.Firstly,a projection pursuit algorithm was used to choose the influence factors,and then the selected impact factors were used as BP neural network input variables to learn and establish gold price forecast model,finally the forecast performance was tested by simulation experiments. The test results show that the combined model can well depict the gold price trend,simplify network structure,accelerate the network learning speed,and improve the prediction accuracy of gold price,which provides a new forecasting method for gold price.