融合传递熵的图神经网络农产品期货预测模型

doi:10.3778/j.issn.1002-8331.2108-0224

摘要/Abstract

摘要： 针对农产品期货价格波动的非线性及国内外期货产品的联动性特征，考虑到传统神经网络预测模型未能针对多源输入变量间的因果关系进行定量表征，构建融合传递熵的图神经网络预测模型。通过计算传递熵表示节点间的邻接矩阵，作为先验信息识别变量间的因果关系；设置多尺寸滤波器的时间卷积模块提取节点特征，用于识别序列时间依赖性；设置图卷积模块实现对节点信息及其邻域信息的传播与特征筛选，最后连接参数，输出最终的预测结果。在大豆期货数据上的实证研究表明，相较于现有的通用预测模型，该模型能够实现最佳的预测效果。

关键词: 农产品期货预测, 图神经网络, 传递熵, 多元时间序列

Abstract: In view of the nonlinear fluctuation of agricultural futures price and the linkage characteristics of domestic and foreign futures products, considering that the traditional neural network prediction model can not quantitatively characterize the causal relationship between multi-source input variables, this paper constructs a graph neural network prediction model with transfer entropy. Firstly, the adjacency matrix between nodes is represented by calculating the transfer entropy, which is used as a priori information to identify the causal relationship between variables. At the same time, the temporal convolution module of multi-scale filter is set to extract the node features to identify the time dependence of the sequence. Secondly, the graph convolution module is set to realize the propagation and feature selection of node information and its neighborhood information. Finally, the final prediction result is output by connecting parameters. The empirical study on soybean futures data shows that compared with the existing general forecasting model, this model can achieve the best forecasting effect.

Key words: agricultural products futures forecasting, graph neural network, transfer entropy, multivariate time series

张杰, 甄柳琳, 徐硕, 翟东升. 融合传递熵的图神经网络农产品期货预测模型[J]. 计算机工程与应用, 2023, 59(2): 321-328.

ZHANG Jie, ZHEN Liulin, XU Shuo, ZHAI Dongsheng. Graph Neural Network Model Based on Transfer Entropy for Agricultural Futures Forecasting[J]. Computer Engineering and Applications, 2023, 59(2): 321-328.

参考文献

[1] 王骏，张宗成.基于VAR模型的中国农产品期货价格发现的研究[J].管理学报，2005（6）：680-684.
WANG J，ZHANG Z C.Study of price discovery of China’s farm produce futures based on VAR model[J].Chinese Journal of Management，2005（6）：680-684.
[2] 刘峰，王儒敬，李传席.ARIMA模型在农产品价格预测中的应用[J].计算机工程与应用，2009，45（25）：238-239.
LIU F，WANG R J，LI C X.Application of ARIMA model in forecasting agricultural product price[J].Computer Engineering and Applications，2009，45（25）：238-239.
[3] 熊涛，鲍玉昆.基于动态模型平均的大豆期货价格预测研究[J].中国管理科学，2020，28（5）：82-91.
XIONG T，BAO Y K.Soybean future prices forecasting based on dynamic model averaging[J].Chinese Journal of Management Science，2020，28（5）：82-91.
[4] JI L，ZOU Y，HE K，et al.Carbon futures price forecasting based with ARIMA-CNN-LSTM model[J].Procedia Computer Science，2019，162：33-38.
[5] LAI G，CHANG W C，YANG Y，et al.Modeling long-and short-term temporal patterns with deep neural networks[C]//The 41st International ACM SIGIR Conference，2018.
[6] SHIH S Y，SUN F K，LEE H Y.Temporal pattern attention for multivariate time series forecasting[J].Machine Learning，2019，108（8/9）：1421-1441.
[7] WU Z，PAN S，LONG G，et al.Connecting the dots：multivariate time series forecasting with graph neural networks[C]//The 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining，2020.
[8] ERMAGUN A，LEVINSON D.Spatiotemporal traffic forecasting：review and proposed directions[J].Transport Reviews，2016：1-29.
[9] TIAN F，YANG K，CHEN L.Realized volatility forecasting of agricultural commodity futures using the HAR model with time-varying sparsity[J].International Journal of Forecasting，2017，33（1）：132-152.
[10] WANG C.Forecast on price of agricultural futures in China based on ARIMA model[J].Asian Agricultural Research，2016（11）：9-12.
[11] ZONG J，ZHU Q.Price forecasting for agricultural products based on BP and RBF Neural Network[C]//IEEE International Conference on Software Engineering & Service Science，2012.
[12] KURUMATANI K.Time series forecasting of agricultural product prices based on recurrent neural networks and its evaluation method[J].SN Applied Sciences，2020，2（8）：1-17.
[13] 贾宁，郑纯军.基于LSTM-DA神经网络的农产品价格指数短期预测模型[J].计算机科学，2019，46（S2）：62-65.
JIA N，ZHENG C J.Short-term forecasting model of agricultural product price index based on LSTM-DA neural network[J].Computer Science，2019，46（S2）：62-65.
[14] PINDYCK R S，ROTEMBERG J J.The excess co-movement of commodity prices[J].The Economic Journal，1990，100：1173.
[15] YU B，YIN H，ZHU Z.Spatio-temporal graph convolutional networks：a deep learning framework for traffic forecasting[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence（IJCAI’18），2017.
[16] MAO X，SHANG P.Transfer entropy between multivariate time series[J].Communications in Nonlinear Science and Numerical Simulation，2016，47：338-347.
[17] LIU C，SUN X，WANG J，et al.Multiscale information transmission between commodity markets：an EMD-based transfer entropy network[J].Research in International Business and Finance，2020，55：101318.
[18] VLAHOGIANNI E I，KARLAFTIS M G，GOLIAS J C.Short-term traffic forecasting：where we are and where we're going[J].Transportation Research Part C Emerging Technologies，2014，43（1）：3-19.
[19] DU S，LI T，YANG Y，et al.Multivariate time series forecasting via attention-based encoder-decoder framework[J].Neurocomputing，2020，388：269-279.
[20] 夏天，程细玉.国内外期货价格与国产现货价格动态关系的研究——基于DCE和CBOT大豆期货市场与国产大豆市场的实证分析[J].金融研究，2006（2）：110-117.
XIA T，CHENG X Y.Research on the dynamic relationship between domestic and foreign futures prices and domestic spot prices--an empirical analysis based on DCE and CBOT soybean futures market and domestic soybean market[J].Journal of Financial Research，2006（2）：110-117.

[21] HWANG S，JEON G，JEONG J，et al.A novel time series based Seq2Seq model for temperature prediction in firing furnace process[J].Procedia Computer Science，2019，155：19-26.

[22] LIANG Y，KE S，ZHANG J，et al.GeoMAN：multi- level attention networks for geo-sensory time series prediction[C]//Twenty-Seventh International Joint Conference on Artificial Intelligence，2018.