计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (2): 125-133.doi: 10.11896/jsjkx.241000110

• 数据库&大数据&数据科学 • 上一篇    下一篇

基于交易行为特征的证券配资账户识别集成模型研究

左旭洪1, 王永全1,2, 邱格屏1   

  1. 1 华东政法大学刑事法学院 上海 201620
    2 华东政法大学智能科学与信息法学系 上海 201620
  • 收稿日期:2024-10-21 修回日期:2024-12-09 出版日期:2025-02-15 发布日期:2025-02-17
  • 通讯作者: 王永全(wangyongquan@ecupl.edu.cn)
  • 作者简介:(2221170089@ecupl.edu.cn)
  • 基金资助:
    国家重点研发计划(2023YFC3306100,2023YFC3306105,2023YFC3306103);国家社会科学基金重大项目(20&ZD199)

Study on Integrated Model of Securities Illegal Margin Trading Accounts Identification Based on Trading Behavior Characteristics

ZUO Xuhong1, WANG Yongquan1,2, QIU Geping1   

  1. 1 School of Law and Criminal Justice,East China University of Political Science and Law,Shanghai 201620,China
    2 Department of Intelligent Science and Information Law,East China University of Political Science and Law,Shanghai 201620,China
  • Received:2024-10-21 Revised:2024-12-09 Online:2025-02-15 Published:2025-02-17
  • About author:ZUO Xuhong,born in 1990,Ph.D candidate,national special economic investigation researcher.His main research interests include data mining and machine learning.
    WANG Yongquan,born in 1964,Ph.D,professor,Ph.D supervisor.His main research interests include big data and artificial intelligence,cyberspace security and cybercrime,digital forensics.
  • Supported by:
    National Key Research and Development Program of China(2023YFC3306100,2023YFC3306105,2023YFC3306103) and Major Projects of National Social Science Foundation(20&ZD199).

PDF (PC)

125

摘要： 针对证券配资账户公开数据稀缺、特征选择不够科学、识别方法研究较少且精度不足等问题,提出基于交易行为特征的证券配资账户识别集成模型(CFS-RF-BP)。该模型包含数据集构建、特征提取、特征选择和账户识别四大核心步骤。根据证券账户交易数据特性,自动生成了模拟数据集,并进行了详细的标记和特征计算;通过异构特征选择模型(CFS-RF),结合对数转换和归一化技术,对17个基本特征进行了重要性评估,从中遴选出5个特征形成关键特征集;在此基础上,采用BP神经网络,构建证券配资账户识别集成模型的分类器,优化该模型的权值和偏置等关键参数,实现了对证券配资账户的自动分类。仿真实验表明,所提出的CFS-RF-BP模型在特征选择、识别的精准率和召回率以及处理效率等方面均取得了显著成效。

关键词: 证券配资, 证券交易数据, 特征提取, 账户识别, 机器学习

Abstract: In response to issues with securities illegal margin trading accounts,such as the scarcity of public data,the unscientific feature selection,the limited research on identification methods that are lack of precision,an integrated model for the identification of securities illegal margin trading accounts based on trading behavior characteristics(CFS-RF-BP) is proposed.This integrated model consists of four main steps:dataset construction,feature extraction,feature selection,and account identification.According to the characteristics of securities account trading data,a simulated dataset is automatically generated,and the relevant features of securities illegal margin trading accounts are detailed labeled and calculated.Using a heterogeneous feature selection model,combined with methods such as logarithm and normalization,the importance of seventeen essential features primarily associated with securities illegal margin trading accounts is evaluated,and five of these features are selected to form a key feature set.Based on this,the BP neural network is employed to construct the classifier for the integrated model of securities margin trading account identification,optimizing key parameters such as weights and biases,thereby achieving automatic classification of securities illegal margin trading accounts.Simulation experiments indicate that the proposed CFS-RF-BP model has achieved excellent results in terms of feature selection,precision,recall rate,and processing efficiency of identification.

Key words: Securities illegal margin trading, Securities trading data, Feature extraction, Account identification, machine learning

中图分类号: 

  • TP391
[1]SHEIKH I,SHEIKH G,EBERLE W.Mining Illegal InsiderTrading of Stocks:A Proactive Approach[C]//2018 IEEE International Conference on Big Data.2018:1397-1406.
[2]Ningxia Regulatory Bureau of China Securities Regulatory Commission.Manifestations and policy boundaries of over-the-coun-ter capital allocation[EB/OL].(2022-06-20)[2024-08-31].http://www.csrc.gov.cn/ningxia/c105510/c3762207/content.shtml.
[3]Shanghai Securities News.Focus on cracking down on systema-tic and large-scale over-the-counter capital allocation,the China Securities Regulatory Commission cooperated with the investigation and punishment of 19 major cases last year[EB/OL].(2022-05-06)[2024-08-31].https://news.stcn.com/news/202105/t20210506_3197077.html.
[4]DENG J,PAN H,YAN H,et al.Disclosing and cooling-off:An analysis of insider trading rules[J].Journal of Financial Economics,2024,160:103913.
[5]LEI J P.Research on the Legal Issues of OTC Capital Allocation:From the Perspective of the Nature of OTC Capital Allocation and Civil Legal Liability[J].Securities Law Review,2016(1):453-462.
[6]HUANG S K.Reflection and Reconstruction on the Determination of the Validity of OTC Allocation Contracts[J].Journal of East China University of Political Science and Law,2021,24(1):125-138.
[7]MIAO Y Z.Determination of the Validity of the Over-the-coun-ter Allocation Contract for Securities Trading and Its Forced Li-quidation Agreement[J].Jurisprudence,2017(5):97-106.
[8]WANG L B.Implicit Guarantee in Financial Innovation:On the Private Law Roots of Financial Crisis[J].Law Review,2016(5):50-63.
[9]MIAO Y Z.Attribute Integration and Regulatory Thinking ofSecurities Trading Allocation under the Pattern of Large Financial Regulation[J].Law Review,2024(1):112-122.
[10]ZHOU X,LI H G.Buying on Margin and Short Selling in an Artificial Double Auction Market[J].Computational Economics,2019,54:1473-1489.
[11]FORTUNE P.Security loans at banks and nonbanks:regulation U[J].New England Economic Review,Fourth Quarter,2002,4:19-40.
[12]LEE K Y.Margin Requirements and Volatility:Evidence from Canadian Stocks[D].Canada:Brock University,2009.
[13]LEE S B,YOO T Y.Margin Regulation and Stock Market Re-sponse:Further Evidence From the U.S.and Some Pacific-Basin Countries[J].Review of Financial Economics,1991,9:79-98.
[14]BASOV S,BHATTI I.Can Short-Selling Prohibition Be Optimal?[J].Islamic Finance in the Light of Modern Economic Theory,2016,12:157-163.
[15]CHEN H,ZHANG M,ZENG J,et al.Artificial intelligence and corporate risk-taking:Evidence from China[J].China Journal of Accounting Research,2024,17(3):100372.
[16]HE Y,YANG P,WANG C S,et al.Research on website recognition based on deep neural network[J].Journal of Sichuan University:Natural Science Edition,2021,3:91-97.
[17]HE B,XING R,LIU D Y,et al.A Method for Identifying Secu-rities Allocation Accounts Based on Supervised Machine Lear-ning:CN201611134189.9[P].CN106709513A[2024-12-10].
[18]HU P,WANG C,ZHANG L,et al.A method for identifying the capital account of the allocator and analyzing the network of the relationship between the capital transaction:CN202111548699.1[P].CN202111548699.1[2024-12-10].
[19]YU J Q,LI S H.Design and Application of Over-the-counter Allocation Recognition Algorithm Based on Machine Learning[J].Microcomputer Applications,2021,37(12):33-47.
[20]SHIH C M,YANG K C,CHAO W P.Predicting stock price using Random Forest algorithm and support vector machines algorithm[C]//2023 IEEE International Conference on Industrial Engineering and Engineering Management.2023:133-137.
[21]SHANG R,GAO L,CHI H,KONG J,et al.Non-convex feature selection based on feature correlation representation and dual manifold optimization[J].Expert Systems with Applications,2024,250:123867.
[22]FU Q,ZHAO D,SHAO L,et al.Magnetic localization algorithm of capsule robot based on BP neural network[J].IEEE Transactions on Instrumentation and Measurement,2024,73:4002509.
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