基于深度学习算法的高频交易策略及其盈利能力

doi:10.3969/j.issn.0253-2778.2018.11.008

中国科学技术大学学报 ›› 2018, Vol. 48 ›› Issue (11): 923-932.DOI: 10.3969/j.issn.0253-2778.2018.11.008

基于深度学习算法的高频交易策略及其盈利能力

孙达昌，毕秀春

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:2018-03-15 修回日期:2018-05-30 接受日期:2018-05-30 出版日期:2018-11-30 发布日期:2018-05-30
通讯作者: 毕秀春
作者简介:孙达昌，男，1992年生，硕士.研究方向：金融工程.E-mail:sdc0124@mail.ustc.edu.cn
基金资助:
国家自然科学基金(14401556,14471304)资助.

High-frequency trading strategies based on deep learning algorithms and their profitability

SUN Dachang, BI Xiuchung

Department of Statistics and Finance, School of Management, University of Science and Technology of China, Hefei 230026, China

Received:2018-03-15 Revised:2018-05-30 Accepted:2018-05-30 Online:2018-11-30 Published:2018-05-30

摘要/Abstract

摘要： 深度学习算法作为机器学习中的一种重要算法，在图像处理、语音识别、机器翻译等领域已成功应用.将深度学习算法应用于高频交易中，选取卷积神经网络和LSTM神经网络分别构建涨跌分类模型，在此基础上提出高频交易策略，并以沥青期货主力合约为例进行回测检验，实证分析策略优良性.通过与人工神经网络高频交易策略的比较，回测检验结果表明基于卷积神经网络和LSTM神经网络的高频交易策略的盈利能力较强，泛化能力较好，两种策略的胜率和期望收益虽有所差异，但均比人工神经网络高频交易策略高.

关键词: 深度学习, 卷积神经网络, LSTM神经网络, 量化投资, 高频交易

Abstract: As an important algorithm, deep learning has been applied successfully to image processing, speech recognition, machine translation and other fields. Here, deep learning algorithms were applied to high-frequency trading. Convolutional neural network(CNN) and long short-term memory(LSTM) neural network were selected to build up and down classification models, respectively. Based on the models, high-frequency trading strategies were proposed. Then the data of bitumen futures contract was used for back-testing and empirically analyzing the superiority of the strategies. In back-testing, deep learning algorithms were compared with artificial neural network(ANN). The results show that both strategies based on CNN and LSTM neural network exhibit better profitability and generalization ability. In addition, the winning rates and expected returns of the two strategies are also better.

Key words: deep learning, convolutional neural network, LSTM neural network, quantitative investment, high-frequency trading

中图分类号:

F830

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.

SUN Dachang, BI Xiuchung. High-frequency trading strategies based on deep learning algorithms and their profitability[J]. Journal of University of Science and Technology of China, 2018, 48(11): 923-932.

参考文献

［1］
BROGAARD J A. High frequency trading and its impact on market quality[R]. Evanston, IL: Northwestern University, 2010.
[2] ALDRIDGE I. High-Frequency Trading: A Practical Guide to Algorithmic Strategies and Trading Systems[M]. Hoboken, NJ: Wiley, 2010.
[3] MARTINEZ V H, ROSU I. High Frequency Traders, News and Volatility[C]// AFA 2013 San Diego Meetings Paper. Aldan, PA: American Finance Association, 2013.
[4] BROGAARD J, HENDERSHOTT T, RIORDANR. High frequency trading and price discovery[J]. The Review of Financial Studies, 2014, 27(8): 2267-2306.
[5] ANGEL J, MCCABE D. Fairness in financial markets: The case of high frequency trading[J]. Journal of Business Ethics, 2013, 112: 585-595.
[6] HINTON G E, OSINDERO S, TEH Y W.A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18: 1527-1554.
[7] 毛勇华, 桂小林, 李前,等. 深度学习应用技术研究[J]. 计算机应用研究, 2016, 33(11): 3201-3205.
MAO Yonghua, GUI Xiaoling, LI Qian, et al. Study on application technology of deep learning[J]. Application Research of Computers, 2016, 33(11): 3201-3205.
[8] LECUN Y, BENGIO Y, HINTON GE. Deep learning[J]. Nature, 2015, 521(7553): 436.
[9] CIRESAN D, MEIER U, MASCI J, et al. Multi-column deep neural network for traffic sign classification[J]. Neural Networks, 2012, 32: 333-338.
[10] TAIGMAN Y, YANG M, RANZATO M, et al. DeepFace: closing the gap to human-level performance in face verification[C]// Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2014: 1939-1946.
[11] JI S, XU W, YANG M,et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(1): 221-231.
[12] KARPATHY A, TODERICI G, SHETTY S, et al. Pedestrian detection with unsupervised multi-stage feature learning[C]// Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society, 2013: 3626-3633.
[13] HADSELL R, SERMANET P, BEN J, et al. Learning long-range vision for autonomous off-road driving[J]. Journal of Field Robotics, 2009, 26(2): 120-144.
[14] COLLOBERT R, WESTON J, BOTTOU L, et al. Natural language processing (almost) from scratch[J]. Journal of Machine Learning Research, 2011, 12: 2493-2537.
[15] BAHDANAU D, CHO K, BENGIOY. Neural machine translation by jointly learning to align and translate[EB/OL]. [2016-5-19]. https://arxiv.org/abs/1409.0473.
[16] WU Y, SCHUSTER M, CHENZ, et al. Google’s neural machine translation system: Bridging the gap between human and machine translation[EB/OL]. [2016-10-08] https://arxiv.org/abs/1609.08144.
[17] 王宣承. 基于LASSO和神经网络的量化交易智能系统构建—以沪深300股指期货为例[J]. 投资研究, 2014, 33(9): 23-29.
WANG Xuancheng.Construct intelligent quantitative trading systems based on LASSO and ANNs: A case study of CSI300 futures[J]. Review of Investment Studies, 2014, 33(9): 23-29.
[18] 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.
[19] 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, Lithuanian: Vilnius Gediminas Technical University, 2012: 122-127.
[20] PERSIO L D, 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.
[21] LU D W. Agent inspired trading using recurrent reinforcement learning and LSTM neural networks[EB/ OL]. [2017-07-23] https://arxiv.org/abs/1707.07338.
[22] 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 Xiuchung, 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.
[23] 范翔. 基于自动化交易平台的高频交易及统计套利分析和研究[D]. 上海: 复旦大学, 2014.
[24] SILVA E, CASTILHO D, PEREIRA A, et al. A neural network based approach to support the market making strategies in high-frequency trading[C]// 2014 International Joint Conference on Neural Networks. IEEE, 2014: 845-852.
[25] 张德丰. MATLAB神经网络应用设计[M]. 北京:机械工业出版社,2012.
[26] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088): 533-536.
[27] KRIZHEVSKY A, SUTSKEVER I, HINTON G E．Imagenet classification with deep convolutional neural networks［C］//Advances in Neural Information Processing Systems．Red Hook，NY: Curran Associates，2012: 1097-1105.
[28] HUBEL D H, WIESEL T N. Receptive fields,binocular and functional architecture in the cat’s visual cortex[J]. The Journal of Physiology, 1962, 160(1): 106-154.
[29] FUKUSHIMA K.Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Bioological Cybernetics, 1980, 36(4): 193-202.
[30] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[31] HINTON G E, SRIVASTAVA N, KRIZHEVSKY A, et al. Improving neural networks by preventing co-adaptation of feature detectors[EB/OL]. [2012-07-03] https://arxiv.org/abs/1207.0580.
[32] GRAVES A. Supervised Sequence Labelling with Recurrent Neural Networks[M]. Berlin: Springer, 2012.
[33] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation，1997, 9(8): 1735-1780.
[34] GERS F A, SCHMIDHUBER J, CUMMINS F. Learning to forget:Continual prediction with LSTM[J]. Neural Computation, 2000, 12(10): 2451-2471.

()
()

[1]	魏俣童, 鲍秉坤, 张子祺, 朱进. 不稳定传输中受损视频的低延迟修复方法[J]. 中国科学技术大学学报, 2021, 51(10): 717-724.
[2]	陶陶，柏建树，刘恒，侯书东，郑啸. 基于WGAN反馈的深度学习差分隐私保护方法[J]. 中国科学技术大学学报, 2020, 50(8): 1064-1071.
[3]	王悦，李京. 基于可视化的卷积神经网络优化方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 959-967.
[4]	杜淑颖，杜鹏，丁世飞. 基于CNN的假冒域名识别方法研究[J]. 中国科学技术大学学报, 2020, 50(7): 1019-1025.
[5]	孟徐然，毕秀春，张曙光. 基于生成对抗网络的高频算法及其回测研究[J]. 中国科学技术大学学报, 2020, 50(6): 801-810.
[6]	谷睿哲, 汪平, 郑梦策, 胡红钢, 俞能海. 基于对抗攻击的侧信道防护方案[J]. 中国科学技术大学学报, 2020, 50(10): 1343-1358.
[7]	熊军林, 赵铎. 基于RGB图像的二阶段机器人抓取位置检测方法[J]. 中国科学技术大学学报, 2020, 50(1): 1-10.
[8]	杜炤鑫, 谢海宁, 宋杰, 周德生, 邹晓峰, 陈冉, 曾平. 基于图像处理和深度学习的配网跳闸故障识别方法[J]. 中国科学技术大学学报, 2020, 50(1): 39-48.
[9]	曾伟辉，李淼，张健，黄小平，王敬贤，袁媛. 面向农作物病害识别的高阶残差卷积神经网络研究[J]. 中国科学技术大学学报, 2019, 49(10): 781-790.
[10]	杨子文，陈蕾，浦建宇. 基于两层迁移卷积神经网络的抽象图像情感识别[J]. 中国科学技术大学学报, 2019, 49(1): 40-48.
[11]	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.
[12]	陈东杰，张文生，杨阳. 基于深度学习的高铁接触网定位器检测与识别[J]. 中国科学技术大学学报, 2017, 47(4): 320-327.
[13]	张皓，吴建鑫，. 集成最大汇合: 最大汇合时只有最大值有用吗[J]. 中国科学技术大学学报, 2017, 47(10): 799-807.

基于深度学习算法的高频交易策略及其盈利能力

High-frequency trading strategies based on deep learning algorithms and their profitability

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 13

编辑推荐

Metrics

本文评价