计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (11A): 230300131-6.doi: 10.11896/jsjkx.230300131

• 交叉&应用 • 上一篇    下一篇

基于模型融合思想的程序化交易投资者识别研究

袁钰坤1, 徐刚1, 吴畏1, 徐力2   

  1. 1 中证数据有限责任公司 北京 100032
    2 中国科学院计算技术研究所网络数据科学与技术重点实验室 北京 100190
  • 发布日期:2023-11-09
  • 通讯作者: 徐刚(xug@csdata.cn)
  • 作者简介:(yuanstanly123@163.com)
  • 基金资助:
    国家自然科学基金(61902380);北京市科技新星计划(Z201100006820061)

Study on Programmatic Trading Investors Recognition Based on Model Fusion

YUAN Yukun1, XU Gang1, WU Wei1, XU Li2   

  1. 1 China Securities Data CO,.LTD,Beijing 100032,China
    2 Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China
  • Published:2023-11-09
  • About author:YUAN Yukun,born in 1994,postgraduate.His main research interests include machine learning and natural language processing.
    XU Gang,born in 1969,postgraduate.His main research interests include data mining and quantitative finance.
  • Supported by:
    National Natural Science Foundation of China(61902380) and Beijing Nova Program(Z201100006820061).

PDF (PC)

207

摘要： 近年来,随着信息化、电子化技术在金融市场中快速发展,程序化交易成为了越来越多金融机构选择的交易方式,对证券期货市场的影响力也逐渐增强,已受到监管层及广大投资者的关注。文中基于模型融合的思想,构建了程序化交易投资者的识别模型,将专家规则与机器学习算法进行叠加融合,并在中国A股市场投资者交易数据上验证了模型的有效性。研究表明,模型能以超过90%的准确率和召回率识别出程序化交易投资者账户,超过了当下的前沿效果,相关研究成果可以为证券期货行业程序化交易识别相关的科技监管工作提供支持。

关键词: 程序化交易,模型融合,机器学习,识别模型,科技监管

Abstract: Programmatic trading has recently gained popularity among financial institutions due to the advancements of information and electronic technology in the financial market.It makes a significant impact on futures markets and draws the attention of regulators and investors.This paper develops recognition models based on the idea of model fusion for programmatic trading investors,combing the rule-based models and machine learning models,and proves the validity of the model on investor data in China’s A-share market.The proposed model achieves over 90% accuracy and recall on recognizing programmatic trading accounts,which is better than the state of the art.Our experiments show that the proposed model is able to support the technical regulation on programmatic trading.

Key words: Programmatic trading, Model fusion, Machine learning, Recognition model, Technical regulation

中图分类号: 

  • TP391
[1]WU L H.Yi Huiman:Research and launch of relevant measures to further expand opening up[N].Economic Information Daily,2021-09-07(1).
[2]BA S S,WANG Y C.The impact of high-frequency trading on securities market:aA review[J].Securities Market Herald,2019(7):42-51.
[3]XIONG X,YUAN H L,ZHANG W,et al.Program trading and its risk analysis [J].Journal of UESTC(Social Sciences Edition),2011,13(3):32-39.
[4]LU Y.Development status,problems and suggestions of pro-grammatic trading in China’s capital market[J].Chinese and Foreign Entrepreneur,2015(1):106.
[5]XIANG Y T,SUN Y H,ZHENG J H,et al.International trend and enlightenment of high-frequency trading regulation[J].Review of Financial Development,2015(9):51-56.
[6]ZHANG M X.Frequent Cancellation and Market Manipulation Determination of High-frequency Trading:From the Perspective of False Statement Manipulation Case of US Treasury Futures[J].Securities Market Herald,2016(5):73-78.
[7]BOEHMER E,FONG K,WU J.International evidence on algorithmic trading[C]//AFA 2013 San Diego Meetings Paper.2012:35-82.
[8]HENDERSHOTT T,JONES C M,MENKVELD A J.Does algorithmic trading improve liquidity?[J].The Journal of Finance,2011,66(1):1-33.
[9]JENNIFE R,CONRA D,SUNI L,et al.High-frequency quoting,trading,and the efficiency of prices[J].Journal of Financial Economics,2015,116(2):271-291.
[10]YU Y R.Research on the relationship between treasury bondfutures and spot prices based on high-frequency data[D].Harbin:Harbin Institute of Technology,2017.
[11]KIRILENKO A,KYLE A S,SAMADI M,et al.The flashcrash:High frequency trading in an electronic market[J].The Journal of Finance,2017,72(3):967-998.
[12]CONRAD J,WAHAL S,XIANG J.High-frequency quoting,trading,and the efficiency of prices[J].Journal of Financial Economics,2015,116(2):271-291.
[13]HENDERSHOTT T,MOULTON P C.Automation,speed,and stock market quality:The NYSE’s hybrid[J].Journal of Financial Markets,2011,14(4):568-604.
[14]BARON M,HAGSTRMER B,KIRILENKO A.Risk and Re-turn in High-Frequency Trading[J].GRU Working Paper Series,2017,53(3).
[15]CLARK C.How to keep markets safe in the era of high-speed trading?[J].Chicago Fed Letter,2012(303):1.
[16]BROGAARD J,CARRION A,MOYAERT T,et al.High frequency trading and extreme price movements[J].Journal of Financial Economics,2018,128(2):253-265.
[17]BUDISH E,CRAMTON P,SHIM J.The high-frequency trading arms race:Frequent batch auctions as a market design response[J].The Quarterly Journal of Economics,2015,130(4):1547-1621.
[18]MENKVELD A J.High-Frequency Traders and Market Structure[J].Financial Review,2014,49(2):333-344.
[19]MENG X J,MENG X L,HU Y.Research on investor sentiment index based on text mining and Baidu index[J].Macroeconomic Research,2016(1):144-153.
[20]ZHANG Y,XIONG Y,KONG X N,et al.IGE+:A Framework for Learning Node Embeddings in Interaction Graphs[J].IEEE Transactions on Knowledge and Data Engineering,2021,33(3):1032-1044.
[21]WU X L,LI J G,WANG Z M.The impact of high-frequency trading on the market[J].Tsinghua Financial Review,2016(2):16-24.
[22]YUAN Y K.Application of artificial intelligence in securitiesmarket supervision[J].Information Technology and Standardization,2019(5):15-19.
[23]HUANG D L,WEN F H,YANG X G.Investor sentiment index and empirical evidence of China’s stock market[J].Systems Science and Mathematics,2009,29(1):1-13.
[24]MENG H.International experience of high-frequency tradingsupervision[J].Journal of Financial Market Research,2014(1):98-102.
[25]FU Q.Research on risk early warning of China’s stock market in the post-stock reform era based on support vector machine[D].Chengdu:Chengdu University of Technology,2014.
[26]ZOU J J,ZHANG Z Y,QIN Z.Application of GARCH model in calculating the value at risk of China’s stock market[J].Systems Engineering-Theory & Practice,2003(5):20-25,135.
[27]YUAN Y K,LI G,ZHAO Z X,et al.Research on influencingfactors of stock market inflection point based on machine learning[J].Computer Science,2021,48(S1):165-168,177.
[28]YE W.Risk control strategy of programmatic trading in China’s capital market[J].Securities Market Herald,2014(8):46-52.
[29]YONG C.Research on high-frequency trading supervision in securities and futures market[J].Finance and Economics,2019(2):83-87.
[30]JIANG Z.Research on potential risks and regulatory system of programmatic trading[J].Research on Financial Regulation,2017(6):78-94.
[31]LUO Z L.Research on international experience in programmatic trading regulation and legislation[C]// China Futures Association.China Futures Association,2016.
[32]ZHANG P P.High-frequency trading regulation from the perspective of Everbright oolong finger incident[J].Journal of Financial Development,2013(10):57-60.
[33]LU S.On the identification of high-frequency trading manipulation market and its legal regulation[J].Social Science Dynamics,2017(9):68-76.
[34]XU G B,ZHANG W.DeepEye:A programmatic transaction recognition and classification method based on deep learning[J].Big Data,2018,4(5):94-102.
[35]GUO C G,CUI E T,XIONG X P.The Enlightenment of Overseas High-frequency Trading Regulatory System on China’s Futures Market Supervision-Based on the Perspective of Economic and Technical Means[J].Journal of Financial Development Research,2021(2):65-72.
[36]ZHU W H,ZHANG W.Research on the regulatory dynamics and regulatory indicators of programmatic trading in overseas markets[J].The Foreland of Trading Technology,2014(19):28-35.
[37]NIU Z,XIONG Y,ZHANG Y.Rresearch on automatic identification method of investor type based on artificial intelligence[J].The Foreland of Trading Technology,2017(28):57-60.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发