基于VMD-DBO-BiGRU的多因素铁矿石期货价格预测

doi:10.6040/j.issn.1671-9352.0.2025.058

《山东大学学报(理学版)》 ›› 2025, Vol. 60 ›› Issue (9): 121-132.doi: 10.6040/j.issn.1671-9352.0.2025.058

• • 上一篇

基于VMD-DBO-BiGRU的多因素铁矿石期货价格预测

刘福国^1,2,刘圆梦³,石玉峰^3,4*,田茂再¹

1.新疆财经大学统计与数据科学学院, 新疆乌鲁木齐 830012;2.昌吉学院数学与数据科学学院, 新疆昌吉 831100;3.山东大学金融研究院, 山东济南 250100;4.山东大学数学学院, 山东济南 250100

发布日期:2025-09-10
通讯作者: 石玉峰(1970— ),男,教授,博士生导师,博士,研究方向为随机分析、金融数学、金融科技等. E-mail:yfshi@sdu.edu.cn
作者简介:刘福国(1978— ),男,教授,博士研究生,硕士生导师,研究方向为金融数学、数量经济学等. E-mail:lfg53880@cjc.edu.cn;刘圆梦(1999— ),女,硕士研究生,研究方向为金融统计与机器学习. E-mail:302578271@qq.com*通信作者:石玉峰(1970— ),男,教授,博士生导师,博士,研究方向为随机分析、金融数学、金融科技等. E-mail:yfshi@sdu.edu.cn
基金资助:
泰山学者工程(tstp20240803);国家重点研发计划项目(2023YFA1008903);山东省自然科学重大基础研究项目(ZR2023ZD33);大连商品交易所“百校万才”工程研究项目

Multi-factor iron ore futures price prediction based on VMD-DBO-BiGRU

LIU Fuguo^1,2, LIU Yuanmeng³, SHI Yufeng^3,4*, TIAN Maozai¹

1. School of Statistics and Data Science, Xinjiang University of Finance and Economics, Urumqi 830012, Xinjiang, China;
2. School of Mathematics and Data Science, Changji College, Changji 831100, Xinjiang, China;
3. Institute for Financial Studies, Shandong University, Jinan 250100, Shandong, China;
4. School of Mathematics, Shandong University, Jinan 250100, Shandong, China

Published:2025-09-10

摘要/Abstract

摘要： 提出一种结合变分模态分解(variational mode decomposition, VMD)、蜣螂优化算法(dung beetle optimization, DBO)与双向门控循环单元(bidirectional gated recurrent unit, BiGRU)的预测模型(VMD-DBO-BiGRU),旨在提升铁矿石期货价格预测精度。首先,采用VMD方法对铁矿石期货价格序列进行模态分解,提取不同时间尺度的价格特征并抑制噪声干扰;其次,引入DBO算法优化BiGRU模型的超参数,避免传统优化方法易陷入局部最优的问题;最后,将优化后的BiGRU模型应用于各模态分量的预测,并根据预测结果线性重构得到最终的期货价格预测值。实证研究表明,本文模型在单步和多步预测中均显著提高了铁矿石价格的预测精度,并较基准模型展现出持续的预测性能优势,为山东某钢厂等相关企业在套期保值策略制定和投资决策分析中提供了技术支持,有助于降低市场风险并提高决策效率。

关键词: 铁矿石期货价格, 变分模态分解, 蜣螂优化算法, 双向门控循环单元

Abstract: By integrating variational mode decomposition(VMD), the dung beetle optimization(DBO)and the bidirectional gated recurrent unit(BiGRU), a price prediction model(VMD-DBO-BiGRU)is proposed, aiming to enhance iron ore futures prediction accuracy. First, VMD is employed to decompose the iron ore futures price series into different modal components, extracting multi-scale price features while suppressing noise. Then, DBO is utilized to optimize the hyperparameters of the BiGRU model, mitigating the risk of local optimum associated with traditional optimization methods. Finally, the optimized BiGRU model is applied to predict each decomposed component, and the final futures price prediction is obtained by linear reconstruction of the predicted results. Experimental findings demonstrate that the proposed model significantly improves prediction accuracy in both single-step and multi-step forecasting, consistently outperforming benchmark models. Moreover, this model provides robust technical support for hedging and investment decision-making in enterprises such as a steel plant in Shandong, contributing to risk mitigation and improved decision efficiency.

Key words: iron ore futures price, variational mode decomposition, dung beetle optimization algorithm, bidirectional gated recurrent unit

中图分类号:

O211

刘福国,刘圆梦,石玉峰,田茂再. 基于VMD-DBO-BiGRU的多因素铁矿石期货价格预测[J]. 《山东大学学报(理学版)》, 2025, 60(9): 121-132.

LIU Fuguo, LIU Yuanmeng, SHI Yufeng, TIAN Maozai. Multi-factor iron ore futures price prediction based on VMD-DBO-BiGRU[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2025, 60(9): 121-132.

参考文献

[1] JIA Lijun, XU Ruoyu, WU Jian, et al. Impacts of geopolitical risk and economic policy uncertainty on metal futures price volatility: evidence from China[J]. Resources Policy, 2023, 87:104328.
[2] PUSTOV A, MALANICHEV A, KHOBOTOLOV I. Long-term iron ore price modeling: marginal costs vs. incentive price[J]. Resources Policy, 2013, 38(4):558-567.
[3] PAN Weixu, LIU Shiqian, KUMRAL M, et al. Iron ore price forecast based on a multi-echelontandem learning model[J]. Natural Resources Research, 2024, 33(5):1969-1992.
[4] 李林泰,崔巍. 铁矿石价格波动的因果推断: 影响因素与效应分析[J]. 技术经济,2024,43(8):36-45. LI Lintai, CUI Wei. Causal inference of iron ore price fluctuations: analysis of influencing factors and effects[J]. Technological Economics, 2024, 43(8):36-45.
[5] 廖正卿. 铁矿石价格影响因素及价格预测[J]. 环渤海经济瞭望,2020,34(4):51-52. LIAO Zhengqing. Influencing factors and price forecasting of iron ore[J]. Economic Outlook of the Bohai Economic Rim, 2020, 34(4):51-52.
[6] 周慧勤,陈婷,何建军. 铁矿石价格影响因素及价格预测研究[J]. 中国物价,2018,6:55-57. ZHOU Huiqin, CHEN Ting, HE Jianjun. Research on influencing factors and price forecasting of iron ore[J]. China Price, 2018, 6:55-57.
[7] 王维. 我国进口铁矿石价格影响因素分析[J]. 中国物价,2017,2:58-61. WANG Wei. Analysis of influencing factors of imported iron ore prices in China[J]. China Price, 2017, 2:58-61.
[8] 邵留国,许自花,张仕璟. 新市场格局下铁矿石价格影响因素研究[J]. 管理评论,2018,30(2):13-24,41. SHAO Liuguo, XU Zihua, ZHANG Shijing. Research on influencing factors of iron ore prices under the new market pattern[J]. Management Review, 2018, 30(2):13-24,41.
[9] 王忠康,顾晓薇,胥孝川,等. 基于加权移动平均法的铁矿石价格预测[J]. 中国矿业,2017,26(7):31-34. WANG Zhongkang, GU Xiaowei, XU Xiaochuan, et al. Iron ore price forecasting based on weighted moving average method[J]. China Mining, 2017, 26(7):31-34.
[10] 许可,刘静怡. 基于VAR-TARCH模型的铁矿石期货价格发现功能实证研究[J]. 中国证券期货,2020,3:21-31. XU Ke, LIU Jingyi. Empiricalstudy on the price discovery function of iron ore futures prices based on VAR-TARCH model[J]. China Securities and Futures, 2020, 3:21-31.
[11] 斯燕,陈艺. 基于LSTM神经网络模型的铁矿石期货市场实证研究[J]. 中国集体经济,2024(2):100-103. SI Yan, CHEN Yi. Empirical study on iron ore futures market based on LSTM neural network model[J]. China Collective Economy, 2024(2):100-103.
[12] 施焕伟. 铁矿石期货价格预测及其套期保值策略研究[D]. 北京:中国石油大学(北京),2021. SHI Huanwei. Research on iron ore futures price forecasting and hedging strategy[D]. Beijing: China University of Petroleum(Beijing), 2021.
[13] 沈欣宜,李旭,沈虹. 基于机器学习的铜期货价格预测分析[J]. 扬州大学学报(自然科学版),2021,24(5):1-7. SHEN Xinyi, LI Xu, SHEN Hong. Forecasting analysis of copper futures prices based on machine learning[J]. Journal of Yangzhou University(Natural Science Edition), 2021, 24(5):1-7.
[14] 邓龙鑫. 基于混沌时间序列和机器学习的铁矿石价格预测模型研究[D]. 长沙:中南大学,2022. DENG Longxin. Research on iron ore price forecasting model based on chaos time series and machine learning[D]. Changsha: Central South University, 2022.
[15] 廖婧文. 基于VMD-LSTM-ELMAN模型的国际原油价格人工智能预测研究[J]. 成都理工大学学报(自然科学版),2024,51(1):164-180. LIAO Jingwen. Research on artificial intelligence forecasting of international crude oil prices based on VMD-LSTM-ELMAN model[J]. Journal of Chengdu University of Technology(Natural Science Edition), 2024, 51(1):164-180.
[16] 王瑞,王雨宁,逯静. 基于双分解和深度学习的短期风电功率预测[J/OL]. 武汉大学学报(工学版).(2024-10-08)[2025-04-11]. htttp://kns.cnki.net/kcms/detail/42.1675.T.20241008.1139.004.html. WANG Rui, WANG Yuning, LU Jing. Short-term wind power prediction based on double decomposition and deep learning[J/OL]. Journal of Wuhan University(Engineering Edition).(2024-10-08)[2025-04-11]. http://kns.cnki.net/kcms/detail/42.1675.T.20241008.1139.004.html.
[17] 邹婕,李路. 基于随机森林的SA-BiGRU模型的股票价格预测研究[J]. 中国物价,2023,11:52-56. ZOU Jie, LI Lu. Research on stock price forecasting based on random forest and SA-BiGRU model[J]. China Price, 2023, 11:52-56.
[18] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition[J]. IEEE Transactions on Signalprocessing, 2013, 62(3):531-544.
[19] XUE Jiankai, SHEN Bo. Dung beetle optimizer: a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing, 2023, 79(7):7305-7336.
[20] SHEPARD D. A two-dimensional interpolation function for irregularly-spaced data[C] //Proceedings of the 1968 23rd ACM National Conference. New York: ACM, 1968:517-524.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于VMD-DBO-BiGRU的多因素铁矿石期货价格预测

Multi-factor iron ore futures price prediction based on VMD-DBO-BiGRU

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

多维度评价

本文评价

推荐阅读 0

[1]	吕平涛,王才士,赵积君. 基于Hadamard游荡的一类具有相同特征值和连续谱的两态量子游荡[J]. 《山东大学学报(理学版)》, 2024, 59(8): 84-93.
[2]	高玉峰,冯德成. 条件弱鞅和条件N-弱鞅的上(下)穿不等式[J]. 《山东大学学报(理学版)》, 2024, 59(6): 122-126.
[3]	张亚茹,夏莉,张典秋. 混合双分数布朗运动下的永久美式回望期权定价[J]. 《山东大学学报(理学版)》, 2024, 59(4): 98-107.
[4]	严晓东. 策略极限理论与策略统计学习[J]. 《山东大学学报(理学版)》, 2024, 59(1): 1-10, 45.
[5]	徐诚浩,王开永. 二维离散时间风险模型的破产概率[J]. 《山东大学学报(理学版)》, 2023, 58(11): 27-34, 52.
[6]	杨鹏,张晓燕. 基于Stackelberg博弈的最优再保险合同设计[J]. 《山东大学学报(理学版)》, 2023, 58(11): 1-14,26.
[7]	张诗苗,吕艳. 带Lévy噪声的Lotka-Volterra竞争模型的参数估计[J]. 《山东大学学报(理学版)》, 2023, 58(10): 24-31.
[8]	丁佳鑫,郭永峰,米丽娜. 高斯噪声和Lévy噪声激励下欠阻尼周期势系统的相变行为[J]. 《山东大学学报(理学版)》, 2023, 58(8): 111-117.
[9]	高琦,戴洪帅,武艳华. 基于MPEWMA控制图的串联排队网络的监测与控制[J]. 《山东大学学报(理学版)》, 2023, 58(8): 104-110, 117.
[10]	陈叶君,丁惠生. 带有Stepanov概周期系数的无穷维随机微分方程的θ-概周期解[J]. 《山东大学学报(理学版)》, 2023, 58(6): 113-126.
[11]	周玉兰,李转,李晓慧. 连续时间Guichardet-Fock空间中修正随机梯度算子的性质[J]. 《山东大学学报(理学版)》, 2018, 53(12): 62-68.
[12]	李永明,聂彩玲,刘超,郭建华. 负超可加阵列下非参数回归函数估计的相合性[J]. 《山东大学学报(理学版)》, 2018, 53(12): 69-74.
[13]	陈昊君,郑莹,马明,边莉娜,刘华. 自激滤过泊松过程的协方差[J]. 《山东大学学报(理学版)》, 2018, 53(12): 75-79.
[14]	李小娟,高强. 次线性期望框架下乘积空间的正则性[J]. 山东大学学报（理学版）, 2018, 53(4): 66-75.
[15]	马明,边莉娜,刘华. 基于事件点联合分布的自激滤过泊松过程的低阶矩[J]. 山东大学学报（理学版）, 2018, 53(4): 55-58.