欢迎您访问《智慧农业（中英文）》官方网站！ English
智慧农业

Smart Agriculture ›› 2022, Vol. 4 ›› Issue (4): 156-163.doi: 10.12133/j.smartag.SA20220712

• 信息处理与决策 • 上一篇    

基于深度学习的玉米和大豆期货价格智能预测

许钰林1,2(), 康孟珍1,2(), 王秀娟1,3, 华净1,4, 王浩宇1,4, 沈震1,2   

  1. 1.中国科学院自动化研究所 复杂系统管理与控制国家重点实验室，北京 100109
    2.中国科学院大学 人工智能学院，北京 100049
    3.北京智能化技术与系统工程技术研究中心，北京 100190
    4.青岛中科慧农科技有限公司，山东 青岛 266000
  • 收稿日期:2022-07-27 出版日期:2022-12-30
  • 基金资助:
    国家自然科学基金(62076239)
  • 作者简介:许钰林（1998－），女，硕士研究生，研究方向为计算智能。E-mail：xuyulincs@126.com
  • 通信作者: 康孟珍（1975－），女，博士，副研究员，研究方向为计算植物和智慧农业。E-mail：mengzhen.kang@ia.ac.cn

Corn and Soybean Futures Price Intelligent Forecasting Based on Deep Learning

XU Yulin1,2(), KANG Mengzhen1,2(), WANG Xiujuan1,3, HUA Jing1,4, WANG Haoyu1,4, SHEN Zhen1,2   

  1. 1.The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
    2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
    3.Beijing Engineering Research Center of Intelligent Systems and Technology, Beijing 100190, China
    4.Qingdao Agri Tech Co. , Ltd. , Qingdao 266000, China
  • Received:2022-07-27 Online:2022-12-30
  • corresponding author: KANG Mengzhen, E-mail：mengzhen.kang@ia.ac.cn
  • About author:XU Yulin,E-mail：xuyulincs@126.com
  • Supported by:
    National Natural Science Foundation of China (62076239)

在线阅读

139

知网下载

本地下载

1145

摘要：

玉米和大豆为同季旱粮作物，“争地”矛盾十分突出，同时掌握玉米和大豆两者的价格是必要的。相较于现货，农产品期货价格具有价格发现功能。因此，玉米和大豆期货价格分析和预测对种植结构调整和农户作物品种选择均具有重要意义。本研究首先分析了玉米和大豆期货价格的相关性，通过相关性计算和格兰杰因果检验，发现玉米和大豆期货具有较强的正向相关性，且大豆期货价格是玉米期货价格的格兰杰原因；其次，基于长短时记忆（Long Short-Term Memory，LSTM）模型对玉米和大豆期货价格进行预测，并引入注意力机制（Attention）对期货价格预测模型行优化。对比结果表明，与差分整合移动平均自回归模型（Autoregressive Integrated Moving Average Model，ARIMA）和支持向量回归模型（Support Vector Regression，SVR）相比，LSTM模型在各项指标中均为更优，而与单一的LSTM模型相比，加入Attention机制的Attention-LSTM模型在各项指标中均更优。其中，玉米和大豆期货预测结果的平均绝对误差（Mean Absolute Error，MAE）分别提升3.8%和3.3%，均方根误差（Root Mean Square Error，RMSE）分别提升0.6%和1.8%，平均绝对百分误差（Mean Absolute Percentage Error，MAPE）分别提升4.8%和2.9%，证明了Attention机制的加入可以帮助模型提取有效信息，提升性能。最后，使用LSTM模型结合大豆期货历史价格共同预测玉米期货价格，MAE提升了6.9%、RMSE提升了1.1%、MAPE提升了5.3%。试验结果表明，本研究使用Attention-LSTM模型对玉米和大豆期货价格进行预测，相较于通用预测模型，Attention-LSTM模型能够提高大豆和玉米期货价格预测精度，且结合相关农产品期货价格数据，可以提升单个农产品期货模型的预测性能。

关键词: 玉米和大豆期货, 期货价格预测, 长短时记忆模型, Attention机制, 深度学习, 支持向量回归

Abstract:

Corn and soybean are upland grain in the same season, and the contradiction of scrambling for land between corn and soybean is prominent in China, so it is necessary to explore the price relations between corn and soybean. In addition, agricultural futures have the function of price discovery compared with the spot. Therefore, the analysis and prediction of corn and soybean futures prices are of great significance for the management department to adjust the planting structure and for farmers to select the crop varieties. In this study, the correlation between corn and soybean futures prices was analyzed, and it was found that the corn and soybean futures prices have a strong correlation by correlation test, and soybean futures price is the Granger reason of corn futures price by Granger causality test. Then, the corn and soybean futures prices were predicted using a long short-term memory (LSTM) model. To optimize the futures price prediction model performance, Attention mechanism was introduced as Attention-LSTM to assign weights to the outputs of the LSTM model at different times. Specifically, LSTM model was used to process the input sequence of futures prices, the Attention layer assign different weights to the outputs, and then the model output the prediction results after a layer of linearity. The experimental results showed that Attention-LSTM model could significantly improve the prediction performance of both corn and soybean futures prices compared to autoregressive integrated moving average model (ARIMA), support vector regression model (SVR), and LSTM. For example, mean absolute error (MAE) was improved by 3.8% and 3.3%, root mean square error (RMSE) was improved by 0.6% and 1.8% and mean absolute error percentage (MAPE) was improved by 4.8% and 2.9% compared with a single LSTM, respectively. Finally, the corn futures prices were forecasted using historical corn and soybean futures prices together. Specifically, two LSTM models were used to process the input sequences of corn futures prices and soybean futures prices respectively, two parameters were trained to perform a weighted summation of the output of two LSTM models, and the prediction results were output by the model after a layer of linearity. The experimental results showed that MAE was improved by 6.9%, RMSE was improved by 1.1% and MAPE was improved by 5.3% compared with the LSTM model using only corn futures prices. The results verify the strong correlation between corn and soybean futures prices at the same time. In conclusion, the results verify the Attention-LSTM model can improve the performances of soybean and corn futures price forecasting compared with the general prediction model, and the combination of related agricultural futures price data can improve the prediction performances of agricultural product futures forecasting model.

Key words: corn and soybean futures, futures price forecast, LSTM model, Attention, deep learning, support vector regression

中图分类号: 

京ICP备09089781号-37