以2011年1月至2016年7月的国债月度数据为样本,研究了在利率期限结构预测中,反向传播神经网络(BPNN)、小波神经网络(WNN)、径向基神经网络(RBFNN)和广义回归神经网络(GRNN)4种网络中相关参数的设定对精度的影响,并对预测效果进行实证比较。研究结果表明:广义回归神经网络预测效果较好,反向传播神经网络预测结果波动性较小,小波神经网络和径向基神经网络预测结果波动性较大。
The study sample selected in this paper is the monthly government bonds data from January 2011 to July 2016. We study the effect of related parameters which are selected for back propagation neural network (BPNN) , wavelet neural network (WNN) , radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) on the prediction accuracy, and compare the prediction results of the four types of neural networks empirically. The results demonstrate that the GRNN performs best and the prediction results of the BPNN have smaller volatility, whilst the WNN and RBFNN prediction results are more volatile.