摘要
通过对小波神经网络的分析,建立了小波神经网络模型,使其具有更好的预测性能。然后利用该模型对深圳300成分指数(2010—06—01到2010—09—30)进行了非线性逼近。通过Matlab软件对该网络的训练进行了数值仿真。仿真结果表明:该网络模型对金融时间序列进行预测是可行的。
Based on the analysis of wavelet neural network,the paper established a wavelet neural network model,and made its have better forecasting performance.By means of model,it made the nonlinear approximation using 300 pieces of Shenzhen composition index.The software Matlab was used to train the network,and then the trained network was adopted to perform the numerical simulation.The simulation results show that the network model of financial time series forecast is feasible.
出处
《重庆理工大学学报（自然科学）》
CAS
2011年第6期49-52,共4页
Journal of Chongqing University of Technology：Natural Science
基金
国家自然科学基金资助项目(408034)
甘肃省自然科学基金资助项目(3ZS051-A25-030
3ZS-042-B25-049)
兰州交通大学科研基金资助项目(DXS2010-018)
关键词
小波神经网络
深圳300成分指数
预测
数值仿真
wavelet neural network
shenzhen composition index
forecast
numerical simulation
