基于信号分解降噪的CNN-BiLSTM金融市场趋势预测  

CNN-BiLSTM Financial Market Trend Prediction based on Signal Decomposition and Noise Reduction

作　　者：戴宇睿 安俊秀[1] 李焯炜 DAI Yurui;AN Junxiu;LI Zhuowei(College of Software Engineering,Chengdu University of Information Technology,Chengdu 610225,China)

机构地区：[1]成都信息工程大学软件工程学院,四川成都610225

出　　处：《成都信息工程大学学报》2023年第1期28-36,共9页Journal of Chengdu University of Information Technology

基　　金：国家自然科学基金资助项目(71673032)。

摘　　要：随着金融时间序列数据日趋复杂,如何捕捉金融数据未来多天的趋势变化成了难题。针对该问题提出了基于信号分解降噪和注意力机制的CNN-BiLSTM金融市场趋势预测模型(attention-based DWT-VMD-CBiLSTM)。首先利用离散小波变换(DWT)对原始金融股指序列进行降噪处理,然后利用变分模态分解(VMD)对降噪后的数据进一步分解为若干子序列。再结合多元基本面特征,利用基于注意力机制的CBiLSTM网络模型对各子序列进行多步预测,最后将各预测结果相加得到最终结果,实现较为长期的趋势预测。为证明所提出的模型性能,在不同金融股指数据集上与不同模型进行了实验比较。结果表明,提出的模型预测精度优于其他方法,在平均绝对误差(MAE)和平均百分比误差(MAPE)上分别达到12.28、0.39和80.27、0.71,在可决系数(R^(2))和可释方差值(EVS)上达到72%、74%和79%、69%的拟合度。With the increasing complexity of financial time series data,it becomes a challenge to capture the trend changes of financial data for multiple days in the future.To address this problem,a financial market trend prediction model(attention-based DWT-VMD-CBiLSTM)based on CNN+BiLSTM with signal decomposition noise reduction and added attention mechanism is proposed.Firstly,the original financial stock index series are noise-reduced by using discrete wavelet transform(DWT),and then the noise-reduced data are further decomposed into several sub-series by using variational modal decomposition(VMD).Based on the first two steps combined with multivariate features,a CNN+BiLSTM network model based on the attention mechanism is used to make multi-step predictions for each sub-series,and finally the prediction results are summed to obtain the final results to achieve longer-term trend prediction.To demonstrate the performance of the proposed model,experimental comparisons are conducted with different models on different financial stock index datasets.The results show that the prediction accuracy of the proposed model outperforms other methods,reaching 12.28,0.39 and 80.27.0.71 in mean absolute error(MAE)and mean percentage error(MAPE),respectively,and 72%,74%and 79%,69%in the coefficient of resolvability(R^(2))and interpretable variance value(EVS)of the fit.

关 键 词：金融时间序列预测 离散小波变换 变分模态分解 CNN 双向LSTM 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]