摘要
利用小波分析对金融时间序列做多尺度分解、去噪,借助改进的粒子群算法对BP神经网络的隐层进行优化,并建立金融时间序列的分层预测模型。实验结果表明,预测效果比直接利用BP神经网络和小波分析结合神经网络的方法都有所提升。
Wavelet analysis is used to multi-scale decomposition and denoising of financial time series.The improved particle swarm optimization（ PSO） algorithm is used to optimize the hidden layer of BP neural network,and then the hierarchical prediction model of financial time series is established. The experimental results show that the prediction effect is better than BP neural network and wavelet analysis combined with the neural network methods.
作者
苗旭东
魏连鑫
MIAO Xu-dong;WEI Lian-xin(The College of Science, University of Shanghai for Science and Technology, Shanghai 200093, Chin)
出处
《信息技术》
2018年第5期26-29,共4页
Information Technology
基金
国家自然科学基金(11301340)
关键词
小波分析
粒子群(PSO)算法
BP神经网络
金融时间序列
wavelet analysis
particle swarm optimization （PSO） algorithm
BP neural network
financial time series
