基于LSTM神经网络的黑色金属期货套利策略模型

doi:10.3969/j.issn.0253-2778.2018.02.006

中国科学技术大学学报 ›› 2018, Vol. 48 ›› Issue (2): 125-132.DOI: 10.3969/j.issn.0253-2778.2018.02.006

基于LSTM神经网络的黑色金属期货套利策略模型

龙奥明，毕秀春，张曙光

1.中国科学技术大学数学科学学院, 安徽合肥 230026；2.中国科学技术大学管理学院统计与金融系，安徽合肥 230026

收稿日期:2017-05-23 修回日期:2017-11-09 出版日期:2018-02-28 发布日期:2018-02-28
通讯作者: 毕秀春
作者简介:龙奥明，男，1992年生，硕士.研究方向：金融工程.E-mail: aomingl@mail.ustc.edu.cn
基金资助:
国家自然科学基金(14401556，14471304)，中央高校基本科研业务费专项资金(WK2040000012)资助.

An arbitrage strategy model for ferrous metal futures based on LSTM neural network

LONG Aoming, BI Xiuchun, ZHANG Shuguang

1. School of Mathematical Sciences, University of Science and Technology of China, Hefei 230026, China;
2. Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei 230026, China）

Received:2017-05-23 Revised:2017-11-09 Online:2018-02-28 Published:2018-02-28

摘要/Abstract

摘要： 利用协整检验方法和LSTM神经网络算法，建立黑色金属期货市场的套利策略模型.利用基于LSTM神经网络套利策略模型对大连商品交易所上市的焦炭期货、铁矿石期货和上海期货交易所上市的螺纹钢期货进行实证研究.对比研究基于LSTM神经网络、BP神经网络和卷积神经网络的3种套利策略模型，实证结果表明基于LSTM神经网络的黑色金属期货套利策略模型可行有效，并且比BP神经网络套利策略模型和卷积神经网络套利策略模型表现更好.

关键词: 黑色金属期货, 跨品种套利, 协整, LSTM神经网络

Abstract: Using the cointegration test method and LSTM neural network algorithm, the arbitrage strategy model for ferrous metal futures market was established. The empirical study is conducted on the coke futures, iron ore futures on the Dalian Commodity Exchange and the rebar futures on the Shanghai Futures Exchange using the arbitrage strategy model based on LSTM neural network. The arbitrage strategy models based on LSTM neural network, BP neural network and convolutional neural network were compared, and the empirical results show that the arbitrage strategy model for ferrous metal futures based on LSTM neural network is feasible and effective, and performs better than the arbitrage strategy models based on BP neural network and convolutional neural network.

Key words: ferrous metal futures, cross-commodity arbitrage arbitrage, cointegration, LSTM neural network

中图分类号:

F830.9

龙奥明，毕秀春，张曙光. 基于LSTM神经网络的黑色金属期货套利策略模型[J]. 中国科学技术大学学报, 2018, 48(2): 125-132.

LONG Aoming, BI Xiuchun, ZHANG Shuguang. An arbitrage strategy model for ferrous metal futures based on LSTM neural network[J]. Journal of University of Science and Technology of China, 2018, 48(2): 125-132.

参考文献

［1］
HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[2] GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget: Continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.
[3] WEN T H, GASIC M, MRKSIC N, et al. Semantically conditioned LSTM-based natural language generation for spoken dialogue systems[C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, PA: Association for Computational Linguistics, 2015: 1711-1721.
[4] DONAHUE J, HENDRICKS A L, GUADARRAMA S, et al. Long-term recurrent convolutional networks for visual recognition and description[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 2015: 2625-2634.
[5] VENUGOPALAN S, XU H, DONAHUE J, et al. Translating videos to natural language using deep recurrent neural networks[J]. Human Language Technologies: The 2015 Annual Conference of the North American Chapter of the ACL. Stroudsburg, PA: Association for Computational Linguistics, 2015: 1494-1504.
[6] MAKNICKIEN N, MAKNICKAS A. Application of neural network for forecasting of exchange rates and forex trading[C]// The 7th International Scientific Conference “Business and Management 2012”. Vilnius, Lithuania: Vilnius Gediminas Technical University, 2012: 10-11.
[7] DI PERSIO L, HONCHAR O. Artificial neural networks architectures for stock price prediction: Comparisons and applications[J]. International Journal of Circuits, Systems and Signal Processing, 2016, 10: 403-413.
[8] SIMON D P. The soybean crush spread: Empirical evidence and trading strategies[J]. Journal of Futures Markets, 1999, 19(3): 271-289.
[9] 仇中群, 程希骏. 基于协整的股指期货跨期套利策略模型[J]. 系统工程, 2008, 26(12): 26-29.
QIU Zhongqun, CHENG Xijun. Calendar spread arbitrage strategy model for index futures based on co-integration rule[J]. Systems Engineering, 2008, 26(12):26-29.
[10] 葛翔宇, 吴洋, 周艳丽. 门限协整套利: 理论与实证研究[J]. 统计研究, 2012,29(3): 79-87.
GE Xiangyu, WU Yang, ZHOU Yanli. Threshold cointegration arbitrage: Theory and application[J]. Statistical Research, 2012, 29(3): 79-87.
[11] KANAMURA T, RACHEV S T, FABOZZI F J. A profit model for spread trading with an application to energy futures[J]. The Journal of Trading, 2010, 5(1): 48-62.
[12] DUNIS C L, LAWS J, EVANS B. Modelling and trading the soybean-oil crush spread with recurrent and higher order networks: A comparative analysis[J]. Neural Network World, 2006, 16(3): 193.
[13] DUNIS C L, LAWS J, MIDDLETON P W, et al. Trading and hedging the corn/ethanol crush spread using time-varying leverage and nonlinear models[J]. The European Journal of Finance, 2015, 21(4): 352-375.
[14] 曾濂, 马丹頔, 刘宗鑫. 基于BP神经网络改进的黄金价格预测[J]. 计算机仿真, 2010 (9): 200-203.
ZENG Lian, MA Dandi, LIU Zongxin. Gold price forecast based on improved BP neural network[J]. Computer Simulation, 2010, 27(9):200-203.
[15] 张金仙, 闫二乐, 杨拴强. 基于自适应 BP 神经网络的上证指数预测模型的研究[J]. 长春大学学报, 2016, 26(6):26-30.
ZHANG Jinxian, YAN Erle, YANG Shuanqiang. Research on prediction model of shanghai stock exchange index based on self-adaptive BP neural network[J]. Journal of Changchun University, 2016, 26(6): 26-30.
[16] 林杰, 龚正. 基于人工神经网络的沪锌期货价格预测研究[J]. 财经理论与实践, 2017, 38(2): 54-57.
LING Jie, GONG Zheng. A research on forecasting of Shanghai zinc futures price based on artificial neural network[J]. The Theory and Practice of Finance and Economics, 2017, 38(2): 54-57.
[17] 张贵勇. 改进的卷积神经网络在金融预测中的应用研究[D]. 郑州：郑州大学, 2016.
ZHANG Guiyong. Research on the application of improved convolutional neural network in financial forecasting[D]. Zhengzhou: Zhengzhou University, 2016.
[18] TSANTEKIDIS A, PASSALIS N, TEFAS A, et al. Forecasting stock prices from the limit order book using convolutional neural networks[C]// 2017 IEEE 19th Conference on Business Informatics. IEEE, 2017:7-12.
[19] GRAVES A. Supervised Sequence Labelling with Recurrent Neural Networks[M]. Berlin: Springer, 2012: 15-35.
[20] ENGLE R F, GRANGER C W J. Co-integration and error correction: Representation, estimation, and testing[J]. Econometrica: Journal of the Econometric Society, 1987,55(2): 251-276.

()
(

[1]	于晓雨，毕秀春，张曙光. 配对交易的最优阈值[J]. 中国科学技术大学学报, 2020, 50(6): 784-792.
[2]	邓辛凝，毕秀春，张曙光. 基于状态相依风险厌恶的最优动态协整配对交易策略[J]. 中国科学技术大学学报, 2019, 49(8): 655-667.
[3]	孙达昌，毕秀春. 基于深度学习算法的高频交易策略及其盈利能力[J]. 中国科学技术大学学报, 2018, 48(11): 923-932.

基于LSTM神经网络的黑色金属期货套利策略模型

An arbitrage strategy model for ferrous metal futures based on LSTM neural network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价