基于多源异构数据的玉米期货价格可解释性预测

管理评论 ›› 2023, Vol. 35 ›› Issue (12): 40-52.

基于多源异构数据的玉米期货价格可解释性预测

曾宇容^1,2, 吴彬溶³, 王林³, 张金隆³

1. 湖北经济学院信息工程学院, 武汉 430205;
2. 湖北省互联网金融信息工程技术研究中心, 武汉 430205;
3. 华中科技大学管理学院, 武汉 430074

收稿日期:2022-05-31 出版日期:2023-12-28 发布日期:2024-01-30
通讯作者: 吴彬溶(通讯作者)，华中科技大学管理学院博士研究生。
作者简介:曾宇容，湖北经济学院信息工程学院教授，博士；王林，华中科技大学管理学院教授，博士生导师，博士；张金隆，华中科技大学管理学院教授，博士。
基金资助:
国家社会科学基金重大项目(20&ZD126)。

Interpretable Corn Futures Price Forecasting with Multivariate Heterogeneous Data

Zeng Yurong^1,2, Wu Binrong³, Wang Lin³, Zhang Jinlong³

1. School of Information Engineering, Hubei University of Economics, Wuhan 430205;
2. Hubei Internet Finance Information Engineering Technology Research Center, Wuhan 430205;
3. School of Management, Huazhong University of Science and Technology, Wuhan 430074

Received:2022-05-31 Online:2023-12-28 Published:2024-01-30

摘要/Abstract

摘要： 玉米期货价格预测和预警工作有助于指导农业经济高质量发展，而自2020年6月以来我国玉米期货价格波动剧烈，亟需准确高效的玉米期货价格预测方法。针对现有研究未充分考虑疫情、政策调控及新闻文本中潜在的预测信息等不足，本文综合考虑了玉米市场的供求关系、政策调整、国际市场冲击、疫情冲击、突发事件的影响等导致玉米价格波动的多重因素，设计了有效的玉米期货价格可解释性预测框架。同时,针对现有玉米期货价格预测可解释性不足的问题，提出了一种新颖的DE-TFT可解释性玉米期货价格预测模型，该模型采用差分进化算法对时域融合变换器(temporal fusion transformers,TFT)的参数进行智能高效的优化。TFT是一种新颖的基于注意力的深度学习模型，将高性能预测与时间动态可解释分析相结合，表现出优异的预测性能。TFT模型可以产生可解释的玉米期货价格预测结果，包括时间步长的注意力分析和输入变量的重要性排序。在实证研究中，潜在狄利克雷分配模型用来分析“中华粮网”收集的玉米新闻资讯和政策调整的内容及主题，卷积神经网络用来提取新闻资讯的潜在预测信息，可解释的实验结果表明，反映国内疫情状况的百度指数“疫情”的引入和量化后的玉米新闻文本特征都能进一步提升玉米期货价格预测的精度。

关键词: 玉米期货价格, 时间序列预测, 可解释性神经网络, 文本挖掘, 深度学习

Abstract: The prediction and early warning of corn futures prices can help guide the high-quality development of the agricultural economy. Since June 2020, the corn futures prices have fluctuated violently, and accurate and efficient corn futures price forecasting methods are urgently needed. Given the problem that the existing researches do not fully consider the pandemic situation, policy regulation, and potential forecast information in news texts, this research, based on both qualitative and quantitative data, proposes an effective forecast framework for corn futures price interpretability, which takes multiple factors into consideration, such as the supply and demand relationship of the corn market, policy adjustments, international market shocks, epidemic shocks, the impact of emergencies and other factors that lead to the fluctuation of corn prices. At the same time, aiming at the problem of insufficient interpretability of existing corn futures price prediction, a novel DE-TFT interpretable corn futures price prediction model is proposed. The differential evolution algorithm is used to efficiently optimize the parameters of the Temporal Fusion Transformers (TFT). TFT is a novel attention-based deep learning model that combines high-performance forecasting with temporal dynamic interpretable analysis, showing excellent performance in forecasting research. The TFT model can produce interpretable corn futures price prediction results, including attentional analysis of time steps and importance ranking of input variables. In the empirical study, the latent dirichlet allocation topic model is used to analyze the content and topics of corn news information and policy adjustments collected by “China Grain Network”, and the CNN classification model is used to extract the potential prediction information of news information. The interpretable experimental results show that the introduction of the Baidu index “pandemic”, which reflects the domestic epidemic situation and the quantified corn news text features, can further improve the accuracy of corn futures price prediction.

Key words: corn futures price, time series forecasting, interpretable neural networks, text mining, deep learning

曾宇容, 吴彬溶, 王林, 张金隆. 基于多源异构数据的玉米期货价格可解释性预测[J]. 管理评论, 2023, 35(12): 40-52.

Zeng Yurong, Wu Binrong, Wang Lin, Zhang Jinlong. Interpretable Corn Futures Price Forecasting with Multivariate Heterogeneous Data[J]. Management Review, 2023, 35(12): 40-52.

参考文献

[1] Gupta S., Choudhary H., Agarwal D. R. An Empirical Analysis of Market Efficiency and Price Discovery in Indian Commodity Market[J]. Global Business Review, 2018,19(3):771-789
[2] Rezitis A. N. The Relationship between Agricultural Commodity Prices, Crude Oil Prices and US Dollar Exchange Rates: A Panel VAR Approach and Causality Analysis[J]. International Review of Applied Economics, 2015,29(3):403-434
[3] 孟娜,许保光. 基于VAR模型的我国生猪饲料价格影响因素研究[J]. 数理统计与管理, 2011,30(5):761-769
[4] 张利庠,张喜才. 外部冲击对我国农产品价格波动的影响研究——基于农业产业链视角[J]. 管理世界, 2011,(1):71-81
[5] 吴海霞,葛岩,史恒通. 玉米金融化、价格形成机制及政策选择[J]. 管理评论, 2018,30(11):35-45
[6] Fronzetti C. A. Forecasting Election Results by Studying Brand Importance in Online News[J]. International Journal of Forecasting, 2021,36(2):414-427
[7] 朱青,卫柯臻,丁兰琳,等. 基于文本挖掘和自动分类的法院裁判决策支持系统设计[J]. 中国管理科学, 2018,26(1):170-178
[8] 杨晓兰,王伟超,高媚. 股市政策对股票市场的影响——基于投资者社会互动的视角[J]. 管理科学学报, 2020,23(1):15-32
[9] 刘金培,郭艺,陈华友,等. 基于非结构数据流行学习的碳价格多尺度组合预测[J]. 控制与决策, 2019,34(2):279-286
[10] Xu X., Zhang Y. Corn Cash Price Forecasting with Neural Networks[J]. Computers and Electronics in Agriculture, 2021,184:106120
[11] 王珏,胡蓝艺,齐琛. 基于网络关注度的大宗商品市场预测研究[J]. 系统工程理论与实践, 2017,37(5):1163-1171
[12] 王珏,齐琛,李明芳. 基于SSA-ELM的大宗商品价格预测研究[J]. 系统工程理论与实践, 2017,37(8):2004-2014
[13] Xu X. Price Dynamics in Corn Cash and Futures Markets: Cointegration, Causality, and Forecasting through a Rolling Window Approach[J]. Financial Markets and Portfolio Management, 2019,33(2):155-181
[14] Wang J., Li X. A Combined Neural Network Model for Commodity Price Forecasting with SSA[J]. Soft Computing, 2018,22(46):1-11
[15] 王芳,陈俊安. 中国养猪业价格波动的传导机制分析[J]. 中国农村经济, 2009,(7):31-41
[16] 李光泗,曹宝明,马学琳. 中国粮食市场开放与国际粮食价格波动——基于粮食价格波动溢出效应的分析[J]. 中国农村经济, 2015,(8):44-52
[17] 樊琦,祁迪,李霜. 玉米临时收储制度的改革与转型研究[J]. 农业经济问题, 2016,37(8):74-81
[18] 林光华,陈佳鑫. 国内外玉米价格传导效应研究——基于玉米临储政策改革背景下的分析[J]. 价格理论与实践, 2018,4(3):111-114
[19] Fernandez-Diaz J. M., Morley B. Interdependence among Agricultural Commodity Markets, Macroeconomic Factors, Crude Oil and Commodity Index[J]. Research in International Business and Finance, 2019,47:174-194
[20] 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
[21] 刘婷,王凌. 价格支持政策如何影响国内粮食市场期现价格关系——基于玉米和大豆市场的检验[J]. 农业经济问题, 2020,(12):133-144
[22] 李孝忠,吕建兴. 基于贸易管控、价格支持下的中国区域间玉米价格效应研究[J]. 农业技术经济, 2020,(6):4-16
[23] Blei D. M., Ng A. Y., Jordan M. I. Latent Dirichlet Allocation[J]. Journal of Machine Learning Research, 2003,3(4-5):993-1022
[24] 肖毅,熊凯伦,张希. 基于TEI@I方法论的企业财务风险预警模型研究[J]. 管理评论, 2020,32(7):226-235
[25] Li X., Shang W., Wang S. Text-Based Crude Oil Price Forecasting: A Deep Learning Approach[J]. International Journal of Forecasting, 2019,35(4):1548-1560
[26] Lim B., Arik S. O., Loeff N., et al. Temporal Fusion Transformers for Interpretable Multi-Horizon Time Series Forecasting[J]. International Journal of Forecasting, 2021,37(4):1748-1764
[27] 吴江,侯绍新,靳萌萌,等. 基于LDA模型特征选择的在线医疗社区文本分类及用户聚类研究[J]. 情报学报, 2017,36(11):1183-1191
[28] Ray B., Garain A., Sarkar R. An Ensemble-Based Hotel Recommender System using Sentiment Analysis and Aspect Categorization of Hotel Reviews[J]. Applied Soft Computing, 2021,98:106935
[29] Abdi A., Shamsuddin S. M., Hasan S., et al. Deep Learning-Based Sentiment Classification of Evaluative Text Based on Multi-Feature Fusio[J]. Information Processing & Management, 2019,56(4):1245-1259