DeepEye：一个基于深度学习的程序化交易识别与分类方法

doi:10.11959/j.issn.2096-0271.2018053

Abstract

Abstract:

Program trading behavior in A-share market has been systematically analyzed based on the Shanghai Stock Exchange’s latest trading data and a feature indictor system has thus been built up for characterizing and classifying the program trading in the market.Furthermore,based on the deep learning technology,the A-share program trading intelligentized recognition and classification method,DeepEye,has been proposed,which enables program trading behavior in the market to be recognized and classified.The accuracy of the pilot implementation got about 70% which verified the feasibility and effectiveness of the new method.The proposed method can serve as an auxiliary measure to existing investor portraits and behavior supervision analysis for market regulation and can be a reference for improving the existing program trading regulatory rules.

Key words: investor behavior, program trading, behavior supervision, deep learning, classification

CLC Number:

TP393

Guangbin XU, Wei ZHANG. DeepEye:a deep learning-based method of recognition and classification of program trading[J]. Big Data Research, 2018, 4(5): 94-102.

Figures/Tables 6

References 22

[1]	刘逖 . 市场微观结构与交易机制设计高级指南[M]. 上海: 上海人民出版社, 2012 569-583.
	LIU T . Market microstructure and trading mechanism advanced guideline[M]. Shanghai: Shanghai People’s PressPress, 2012: 569-583.
[2]	ALDRIDGE I . High frequency trading[M]. New Jersey: John Wiley ＆ Sons,Inc.Press, 2010: 7-35.
[3]	SEYFERT R . Bugs,predations or manipulations? Incompatible epistemic regimes of high-frequency trading[J]. Economy and Society, 2016,45(2): 251-277.
[4]	叶伟 . 我国资本市场程序化交易的风险控制策略[J]. 证券市场导报, 2014(8): 46-52.
	YE W . The risk control strategies of program trading of Chinese capital market[J]. Securities Market Herald, 2014(8): 46-52.
[5]	熊熊, 袁海亮, 张维 ,等. 程序化交易及其风险分析[J]. 电子科技大学学报(社科版), 2011,13(3): 32-39.
	XIONG X , YUAN H L , ZHANG W ,et al. Program Trading overview and risk analysis[J]. Journal of University Electronics Science and Technology of China, 2011,13(3): 32-39.
[6]	彭蕾 . 中国证券市场程序化交易研究[D]. 成都:西南财经大学, 2005: 4-17.
	PENG L . The research on pr ogram trading of the Chinese securities market[D]. Chengdu:Southwest University of Finance and Economics Press, 2005: 4-17.
[7]	陈梦根 . 算法交易的兴起及最新研究进展[J]. 证券市场导报, 2013(9): 11-17.
	CHEN M G . Algorithmic trading's rising and advances[J]. Securities Market Herald , 2013(9): 11-17.
[8]	蓝海平 . 高频交易的技术特征、发展趋势及挑战[J]. 证券市场导报, 2014(4): 59-64.
	LAN H P . HFT:the technique feature,developments and challenges[J]. Securities Market Herald, 2014(4): 59-64.
[9]	郭朋 . 国外高频交易的发展现状及启示[J]. 证券市场导报, 2012(7): 56-61.
	GUO P . Development of high frequency trading and its implication[J]. Securities Market Herald, 2012(7): 56-61.
[10]	YANG S Y , QIAO Q F , BELING P A ,et al. Gaussian process-based algorithmic trading strategy identification[J]. Quantitative Finance, 2015,15(10): 1683-1702.
[11]	QIAO Q F , BELING P A . Decision analytics and machine learning in economic and financial systems[J]. Environment Systems and Decisions, 2016,36(2): 109-113.
[12]	YANG S Y , QIAO Q F , BELING P A . Algorithmic trading behavior identification using reward learning method[C]// The 2014 International Joint Conference on Neural Networks,July 6-11,2014,Beijing,China. Red Hook:Curran Associates, 2014: 3807-3414.
[13]	张鸿萍 . 基于时间序列交易数据的服装电商客户分类研究[J]. 现代管理, 2017,7(6): 481-492.
	ZHANG H P . Research for customer classification of clothing E-business based on time series transaction data[J]. Modern Management, 2017,7(6): 481-492.
[14]	毛瑞, 费宇 . 基于交易数据的客户分类研究[J]. 中国证券期货, 2012(1): 22-23.
	MAO R , FEI Y . The study of customer classification based on trading data[J]. Securities ＆ Futures of China, 2012(1): 22-23.
[15]	WANG G , ZHANG X , TANG S ,et al. Clickstream user behavior models[J]. ACM Transactions on the Web, 2017,11(4): 1-37.
[16]	BENSON A R , KUMAR R , TOMKINS A . Modeling user consumption sequences[C]// The 25th International Conference on World Wide Web.International World Wide Web Conferences,April 11-15,2016,Montréal,Canada. New York:ACM Press, 2016: 519-529.
[17]	HINTON G E , OSINDERO S , TEH Y W . A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006,18(7): 1527-1554.
[18]	马世龙, 乌尼日其其格, 李小平 ,等. 大数据与深度学习综述[J]. 智能系统学报, 2016,11(6): 728-742.
	MA S L , WUNIRI Q Q G , LI X P ,et al. Deep learning with big data:state of the art and development[J]. CAAI Transactions on Intelligent Systems, 2016,11(6): 728-742.
[19]	SCHMIDHUBER J . Deep learning in neural networks:an overview[J]. Neural Networks, 2015,61(1): 85-117.
[20]	SUTSKEVER I , VINYALS O , LE Q V . Sequence to sequence learning with neural networks[J]. Computer Science, 2014,arXiv:1409.3215.
[21]	孙志远, 鲁成祥, 史忠植 ,等. 深度学习研究与进展[J]. 计算机科学, 2016,43(2): 1-8.
	SUN Z Y , LU C X , SHI Z Z ,et al. Research and ad vances on deep learning[J]. Computer Science, 2016,43(2): 1-8.
[22]	KARNOWSKI T P , AREL I , ROSE D C . Deep spatiotemporal feature learning with application to image classification[C]// The 9th International Conference on Machine Learning and Applications,December 12,2010,Washington,DC,USA. Piscataway:IEEE Computer Society, 2010: 883-888.

Metrics

Recommended 0

No Suggested Reading articles found!

序号	类型	主要行为特征
1	篮子交易	满足推荐规则，有密集多标的报单
2	大单分拆	满足推荐规则，有个股密集报单
3	交易所交易基金（exchange traded fund,ETF）套利	满足推荐规则，有相当头寸的ETF反向交易
4	融券T+0（日内回转交易）	满足推荐规则，个股有相当头寸的信用买卖且无持仓
5	库存T+0	满足推荐规则，个股买卖头寸相当且有持仓
6	特殊账户	满足推荐规则，有大量订单申报但无成交的无成交账户、ETF基金账户和ETF做市商账户
7	混合对冲/调仓	满足推荐规则，整体有头寸相当的买卖
8	其他程序化交易	满足推荐规则，不属于上述分类
9	低频自动化	未达推荐规则，但持续进行低频的自动化报单

序号	指标	特征说明
1	日内申报5笔/s的发生次数	对应推荐规则
2	日内1 s申报并撤销的发生次数	对应推荐规则
3	日内申报笔数	对应推荐规则
4	对冲类型	个股对冲（1）成交个股的买卖量对冲，即\|买量-卖量\|/(买量+卖量)<0.1
		信用交易对冲（2）不属于前一类，且\|股票净买额-融券净卖额\|/(股票净买额+融券净卖额)<0.1
		ETF对冲（3）不属于前两类，且\|股票净买额-ETF净卖额\|/(股票净买额+ETF净卖额)<0.1
		混合对冲（4）不属于前三类，且\|股票净买额-融券净卖额\|/(股票净买额+融券净卖额)<0.1
		非对冲（0）其他情况
5	成交申报比	成交量/申报量，无申报、显著低（<0.1）、低（0.1~0.5）、正常（>0.5）
6	持仓多标的	持仓标的数量达15
7	个股买卖不平衡显著性	成交个股的\|买量-卖量\|/(买量+卖量)，无成交、显著低（<0.1）、中（0.1~0.9）、显著高（>0.9）
8	低频自动化特征	个股申报有连续60个1 min步长滑动窗口（窗口大小为2 min）内均有申报
9	个股密集报单	有个股报单笔数/s达10 笔及以上
10	密集多标的	有申报标的/s达10 只及以上
11	交易多标的	成交标的数量达10 只及以上
12	无/低持仓	无成交、无持仓或持仓量/成交量<0.1、其他

分类	准确率	召回率
识别	67%	60%
分类	72%	—

DeepEye:a deep learning-based method of recognition and classification of program trading

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 6

References 22

Related Articles 15

Metrics

Recommended 0

[1]	Doudou LIU, Baochen JIAO. Research on data asset cataloging of colleges and universities [J]. Big Data Research, 2023, 9(3): 71-84.
[2]	Yimin DENG, Xulong ZHANG, Shijing SI, Jianzong WANG, Jing XIAO. Human avatars synthesis technologies: a survey [J]. Big Data Research, 2023, 9(3): 114-139.
[3]	Yayun HE, Junqing PENG, Jianzong WANG, Jing XIAO. Rhythm dancer: 3D dance generation by keymotion transition graph and pose-interpolation network [J]. Big Data Research, 2023, 9(1): 23-37.
[4]	Yumeng CUI, Jingya WANG, Shangyi YAN, Zhizhong TAO. Automatic key information extraction of police records based on deep learning [J]. Big Data Research, 2022, 8(6): 127-142.
[5]	Xinhui LI, Qing SHEN, Xiongtao ZHANG. Classification algorithm for imbalance data of ECG based on PSOFS and TSK fuzzy system [J]. Big Data Research, 2022, 8(5): 139-152.
[6]	Zhitao ZHU, Shijing SI, Jianzong WANG, Jing XIAO. Survey on federated recommendation systems [J]. Big Data Research, 2022, 8(4): 105-132.
[7]	Jie WANG, Songyan ZHANG, Jiye LIANG. A semi-supervised deep learning algorithm combining consistency regularization and manifold regularization [J]. Big Data Research, 2022, 8(3): 103-114.
[8]	Kangting XU, Wei Song. A Chinese text sentiment analysis method combining language knowledge and deep learning [J]. Big Data Research, 2022, 8(3): 115-127.
[9]	Zhitao ZHAO, Lijun ZHAO, Zheng ZHANG, Ping TANG. Integration of remote sensing intelligent processing algorithm using container cloud technology [J]. Big Data Research, 2022, 8(2): 58-74.
[10]	Xiaolong ZHANG, Long ZHI, Jian GAO, Zhongchen MIAO, Yuefeng LIN, Yali XIANG, Yun XIONG. A semi-supervised learning financial news classification algorithm [J]. Big Data Research, 2022, 8(2): 134-144.
[11]	Feng ZHI, Feng TIAN, Ruofan ZHAO. Classification of big data in metrology [J]. Big Data Research, 2022, 8(1): 60-72.
[12]	Wen SU, Li ZHANG, Xuebing GUO, Honglin HE, Xinzhai TANG, Xiaoli REN. Classification of ecosystem long term observation data product [J]. Big Data Research, 2022, 8(1): 84-97.
[13]	Qiaozhuoran CAO, Zugang CHEN, Guoqing LI, Jing LI. Resource and user access control system of scientific data center [J]. Big Data Research, 2022, 8(1): 98-112.
[14]	Qian SUN, Yongbin QIN, Ruizhang HUANG, Lijuan LIU, Yanping CHEN. Charge prediction method combined with case elements sequence [J]. Big Data Research, 2021, 7(6): 30-40.
[15]	Yu ZHANG, Haibo YUAN, Yanping WANG, Shaowu DONG, Jihai ZHANG. Management control and application of the time-frequency scientific data [J]. Big Data Research, 2021, 7(6): 120-127.