基于多特征融合深度神经网络的玉米期货价格预测

doi:10.16381/j.cnki.issn1003-207x.2022.1040

Abstract

Abstract:

In China's financial and economic system， the futures market of agricultural products plays an important role in guiding the market to self-regulate and providing efficient information transmission for regulators. Effective prediction of futures prices can help guide agricultural production， monitor the operating risks arising from large price fluctuations， and enhance the predictability and pertinence of the national macro-control policies. In this paper， corn futures are taken as the research object，which is the main variety of grain futures. Considering the non-stationary and non-linear characteristics of its price series and the complex market and non-market influencing factors， a deep neural network model with multi-feature fusion is proposed based on the historical trading data of corn futures and relevant news texts. The model uses Bi-directional Long-term and Short-Term Memory neural network （BiLSTM） and text Convolution Neural Network （textCNN） to extract price features and text features respectively， and then fuses the news emotion feature extracted by SnowNLP to predict the closing price of corn futures one step ahead. The effectiveness of the proposed model is verified by setting horizontal and vertical experiments. The empirical results show that the fusion of the three features improves the prediction accuracy of the models most obviously in different feature combination schemes. And compared with the four baseline models， the proposed model shows significant performance advantages on MAE， RMSE and R².

Key words: corn futures price, news text, multi-feature fusion, deep neural network model

CLC Number:

F832.5

Dabin Zhang,Zhimei Zeng,Liwen Ling, et al. Prediction of Corn Futures Price Based on Multi-feature Deep Neural Network Model[J]. Chinese Journal of Management Science, 2026, 34(10): 28-38.

Figures/Tables 13

References 32

[1]	刘慕涵，熊熊. 股指期货交易政策、投资者行为与市场质量［J］. 中国管理科学， 2023，31（7）： 126-139.
	Liu M H， Xiong X. Stock index futures trading policy， investors’Behavior and stock market quality［J］. Chinese Journal of Management Science，2023，31（7）： 126-139.
[2]	赵萌，吴迟. 金融危机对中国农产品期货市场的冲击——基于事件研究法的价格敏感性测试［J］. 农业技术经济， 2010（7）： 4-12.
	Zhao M， Wu C. The impact of financial crisis on China’s agricultural futures market： Price sensitivity test based on event study［J］. Journal of Agrotechnical Economics， 2010（7）： 4-12.
[3]	Chu P K， Hoff K， Molnár P， et al. Crude oil： Does the futures price predict the spot price？［J］. Research in International Business and Finance， 2022， 60： 101611.
[4]	Adämmer P， Bohl M T. Price discovery dynamics in European agricultural markets［J］. Journal of Futures Markets， 2018， 38（5）： 549-562.
[5]	宋波，邢天才. 基于价格发现和统计套期保值的铜期货波动溢出效应检验［J］.统计与决策，2020，36（12）： 148-151.
	Song B， Xing T C. Tiancai.Testing the spillover effect of copper futures volatility based on price discovery and statistical hedging ［J］. Statistics and Decision， 2020， 36（12）： 148-151.
[6]	Kertlly de Medeiros R， da Nóbrega Besarria C， Pitta de Jesus D， et al. Forecasting oil prices： New approaches［J］. Energy， 2022， 238： 121968.
[7]	Zhang W， Gong X， Wang C， et al. Predicting stock market volatility based on textual sentiment： A nonlinear analysis［J］. Journal of Forecasting， 2021， 40（8）： 1479-1500.
[8]	耿立校，刘丽莎，李恒昱. 多源异构数据融合驱动的股票指数预测研究［J］. 计算机工程与应用， 2021， 57（20）： 142-149.
	Geng L X， Liu L S， Li H Y. Research on stock index prediction driven by multi-source heterogeneous data fusion［J］. Computer Engineering and Applications， 2021， 57（20）： 142-149.
[9]	尹海员，寇文娟. 基于朴素贝叶斯法的投资者情绪度量及其对股票特质风险的影响［J］. 中国管理科学， 2024， 32（4）： 38-47.
	Yin H Y， Kou W J. Investor sentiment based on naive Bayes method and its impact on stock idiosyncratic risk［J］. Chinese Journal of Management Science， 2024， 32（4）： 38-47.
[10]	Hochreiter S， Schmidhuber J. Long short-term memory［J］. Neural Computation， 1997， 9（8）： 1735-1780.
[11]	欧阳红兵，黄亢，闫洪举. 基于LSTM神经网络的金融时间序列预测［J］.中国管理科学，2020，28（4）： 27-35.
	Ouyang H B， Huang K， Yan H J. Prediction of financial time series based on LSTM neural network［J］. Chinese Journal of Management Science， 2020， 28（4）： 27-35.
[12]	Siami-Namini S， Tavakoli N， Namin A S. The performance of LSTM and BiLSTM in forecasting time series［C］//Proceedings of the 2019 IEEE International Conference on Big Data （Big Data），Los Angeles， CA， USA，December 9-12， IEEE， 2019： 3285-3292.
[13]	陈可心，黄刚. CStock：一种结合新闻与股价的股票走势预测模型［J］. 计算机技术与发展， 2020， 30（9）： 18-22.
	Chen K X， Huang G. Cstock： A stock trend forecasting model combining news and stock price［J］. Computer Technology and Development， 2020， 30（9）： 18-22.
[14]	Li J， Li G， Liu M， et al. A novel text-based framework for forecasting agricultural futures using massive online news headlines［J］. International Journal of Forecasting， 2022， 38（1）： 35-50.
[15]	Li Y， Jiang S， Li X， et al. The role of news sentiment in oil futures returns and volatility forecasting： Data-decomposition based deep learning approach［J］. Energy Economics， 2021， 95： 105140.
[16]	Bai Y， Li X， Yu H， et al. Crude oil price forecasting incorporating news text［J］. International Journal of Forecasting， 2022， 38（1）： 367-383.
[17]	余传明，龚雨田，王峰，等.基于文本价格融合模型的股票趋势预测［J］.数据分析与知识发现，2018， 2（12）： 33-42.
	Yu C M， Gong Y T， Wang F， et al. Predicting stock prices with text and price combined model［J］.Data Analysis and Knowledge Discovery，2018，2（12）： 33-42.
[18]	徐月梅，王子厚，吴子歆. 一种基于CNN-BiLSTM多特征融合的股票走势预测模型［J］. 数据分析与知识发现， 2021， 5（7）： 126-137.
	Xu Y M， Wang Z H， Wu Z X. Predicting stock trends with CNN-BiLSTM based multi-feature integration model［J］. Data Analysis and Knowledge Discovery， 2021， 5（7）： 126-137.
[19]	Kim Y. Convolutional neural networks for sentence classification［C］//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing （EMNLP），Doha，Qatar， October 25-29 ，ACL， 2014： 1746-1751.
[20]	张冬，魏俊斌. 情感驱动下主流媒体疫情信息数据分析与话语引导策略［J］.图书情报工作， 2021， 65（14）： 101-108.
	Zhang D， Wei J B. Emotion-driven data analysis of mainstream media epidemic information and discourse guidance strategies［J］. Library and Information Service， 2021， 65（14）： 101-108.
[21]	师荣蓉，张教萌. 中国经济高质量发展的社会评价：基于微博情感分析的视角［J］. 统计与决策， 2021， 37（24）： 180-184.
	Shi R R， Zhang J M. Social evaluation of high-quality economic development in China： From the perspective of weibo’s emotional analysis［J］. Statistics & Decision， 2021， 37（24）： 180-184.
[22]	王会娟，陈红佳，高思琴，等. 基于TEI@I方法论的玉米期货价格预测研究［J］. 管理评论， 2020， 32（7）： 293-301.
	Wang H J， Chen H J， Gao S Q， et al. Forecasting corn futures prices based on TEI@I methodology［J］. Management Review， 2020， 32（7）： 293-301.
[23]	Wang J， Wang Z， Li X， et al. Artificial bee colony-based combination approach to forecasting agricultural commodity prices［J］. International Journal of Forecasting， 2022， 38（1）： 21-34.
[24]	Zhang J， Meng Y， Wei J， et al. A novel hybrid deep learning model for sugar price forecasting based on time series decomposition［J］. Mathematical Problems in Engineering， 2021， 2021： 6507688.
[25]	Zhu Q， Zhang F， Liu S， et al. A hybrid VMD-BiGRU model for rubber futures time series forecasting［J］. Applied Soft Computing， 2019， 84： 105739.
[26]	党建武，从筱卿. 基于CNN和GRU的混合股指预测模型研究［J］.计算机工程与应用，2021，57（16）： 167-174.
	Dang J W， Cong X Q. Research on hybrid stock index forecasting model based on CNN and GRU［J］. Computer Engineering and Applications， 2021， 57（16）： 167-174.
[27]	陈标金，谭莹. 信息、交易者情绪与中国农产品期货价格波动［J］. 金融经济学研究， 2017， 32（2）： 66-75.
	Chen B J， Tan Y. Information， trader sentiment and agricultural commodity futures price volatility in China［J］. Financial Economics Research， 2017， 32（2）： 66-75.
[28]	白宗航. 不同流动性水平下投资者情绪对农产品期货价格波动影响研究——基于面板门槛模型的分析［J］. 价格理论与实践， 2019（6）： 116-119.
	Bai Z H. The research on investor sentiment and the volatility of agricultural futures price under different liquidity levels： Based on the panel threshold model［J］. Price （Theory & Practice）， 2019（6）： 116-119.
[29]	Li J， Li G， Liu M， et al. A novel text-based framework for forecasting agricultural futures using massive online news headlines［J］. International Journal of Forecasting， 2022， 38（1）： 35-50.
[30]	Li Y， Jiang S， Li X， et al. The role of news sentiment in oil futures returns and volatility forecasting： Data-decomposition based deep learning approach［J］. Energy Economics， 2021， 95： 105140.
[31]	徐维军，付志能，李茂昌，等. 基于新闻文本挖掘的股指期货高频预测研究［J］. 系统科学与数学， 2021， 41（7）： 1856-1875.
	Xu W J， Fu Z N， Li M C， et al. High-frequency forecasting of stock index futures based on news text mining［J］. Journal of Systems Science and Mathematical Sciences， 2021， 41（7）： 1856-1875.
[32]	Diebold F X， Mariano R S. Comparing predictive accuracy［J］. Journal of Business & Economic Statistics， 1995， 13（3）： 253-263.

日期	当日新闻标题
2012-12-27	山东烟台购销渐显活跃玉米价格暂稳
2012-12-27	黑龙江省双城区玉米价格暂稳
2012-12-28	饲用需求提振玉米有望突破上行
2012-12-28	CBOT玉米期货连跌第二日,受累于美国财政忧虑
…	…
2021-07-29	“烟花”将进入山东京津冀等地风雨强
2021-07-29	上涨情绪进一步上升玉米市场迎来反弹行情
2021-07-30	“暴雨”“烟花”叠加市场炒作天气缺“火候”
2021-07-30	缺乏需求提振玉米淀粉价格或回归震荡调整走势

参数	BiLSTM	textCNN
单层LSTM神经元个数	5	—
卷积核个数	—	100
卷积核大小	—	3，4，5
Dropout	0.25	0.5
Batch_size	16	16
迭代次数	200	200

模型输入	模型	MAE	RMSE	R²
方案一	SVR	0.1187	0.1803	0.3472
	BPNN	0.1601	0.1769	0.3717
	GRU	0.1538	0.1662	0.4457
	BiLSTM	0.1000	0.1078	0.7669
	本文模型	0.0666	0.0764	0.8822
方案二	SVR	0.0790	0.1029	0.7873
	BPNN	0.1389	0.1723	0.4043
	GRU	0.0528	0.0570	0.9347
	BiLSTM	0.0462	0.0584	0.9314
	本文模型	0.0457	0.0548	0.9394
方案三	SVR	0.0786	0.1038	0.7835
	BPNN	0.1317	0.1652	0.4519
	GRU	0.0314	0.0386	0.9702
	BiLSTM	0.0354	0.0432	0.9626
	本文模型	0.0205	0.0280	0.9842

本文模型	对比模型
本文模型	BiLSTM	GRU	BPNN	SVR
proposed	-11.5324^***	-5.9768^***	-19.6933^***	-16.3849^***

Prediction of Corn Futures Price Based on Multi-feature Deep Neural Network Model

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 32

Related Articles 15

Metrics

Comments

Recommended 0

[1]	Zhiqiang Ye, Mengyao Lv, Shunming Zhang, Yan Zhao. Online Media Coverage and Analysts' Earnings Forecast: Based on the Limited Attention Perspective [J]. Chinese Journal of Management Science, 2026, 34(7): 117-126.
[2]	Jinqing Zhang, Suoer Xu. Efficient Portfolios Based on Mean-Variance Shrinkage Estimation under Mixed Normal [J]. Chinese Journal of Management Science, 2026, 34(7): 12-21.
[3]	Haichuan Xu, Hanliang Wang, Weixing Zhou. Measuring Financial Crises: Linking Macroeconomic Price Pressures and Microeconomic Financial Institution Capital Shortfalls [J]. Chinese Journal of Management Science, 2026, 34(5): 44-56.
[4]	Pu Wang, Kunpeng Li, Li Su. Can Dimensionality Reduction Enhance Deep Neural Networks in Learning Credit Risk? ——A Study Based on Factor-Augmented Explainable Learning Models [J]. Chinese Journal of Management Science, 2026, 34(5): 57-71.
[5]	Zhengyang Song, Zhongbao Zhou, Lean Yu, Tiantian Ren. Portfolio Optimization Strategy with a Hybrid Ensemble Forecasting Algorithm and Black-Litterman Model [J]. Chinese Journal of Management Science, 2026, 34(5): 72-85.
[6]	Zezhou Wang, Qifa Xu, Cuixia Jiang. Can Interaction and Dissemination of Mixed-Frequency Information in Companies' Multi-Layer Relationship Networks Improve Asset Pricing? Asset Pricing Study Based on Graph Neural Networks [J]. Chinese Journal of Management Science, 2026, 34(4): 47-62.
[7]	Jixian Meng, Jijia Kang, Qianqian Yang, Xiaoguang Yang. The Impact of Power Rationing Events in 2021 on China's Stock Market [J]. Chinese Journal of Management Science, 2026, 34(3): 25-38.
[8]	Pengqi Liu, Ping Lv. "Winner Picking" or "Winner Avoiding"? Selection Mechanism for Outward Foreign Direct Investment by China's Business Group Affiliates [J]. Chinese Journal of Management Science, 2026, 34(1): 353-368.
[9]	Zhaorong Huang, Zhengyang Song, Bo Yang, Nengmin Zeng, Le’an Yu. Hybrid Multivariate Regression Forecasting for Gold Prices: A Decomposition-Reconstruction-Ensemble Methodology [J]. Chinese Journal of Management Science, 2025, 33(12): 41-56.
[10]	Chao Liu, Lantao Xu. Study on Optimal Portfolio Strategy from the Perspective of Multilayer Temporal Network [J]. Chinese Journal of Management Science, 2025, 33(9): 46-56.
[11]	Jianxin Zhu, Kexin Liu, Nengmin Zeng, Xiong Wu. Competitive Network and Financial Performance: Empirical Evidence Based on Explainable Random Forest [J]. Chinese Journal of Management Science, 2025, 33(8): 75-89.
[12]	Longbing Xu, Wenbin Wu. Over-reaction, Jump Return and A-share Momentum Strategy [J]. Chinese Journal of Management Science, 2025, 33(6): 1-13.
[13]	Weiqi Liu, Jianying Li, Jie Zhou, Dongliang Yuan. Digital Transformation and Firm Value: Theory and Empirical Evidence [J]. Chinese Journal of Management Science, 2025, 33(5): 138-149.
[14]	Xia Liu, Yunyue Zhang, Mengqi Li, Yejun Xu. Quantum Supervised Game Model and Simulation Analysis for Manipulative Behavior in Trading Stock Market [J]. Chinese Journal of Management Science, 2025, 33(3): 24-33.
[15]	Jiaxian Shen, Haozhi Chen, Weiguo Zhang. Research on Systemic Risk Measurement of China’ s Foreign Exchange Market Based on Knowledge Graph Network Characteristics [J]. Chinese Journal of Management Science, 2025, 33(3): 45-61.