The Design of Mean Reversion Strategy Considering Investor Sentiment Basedon Textual Information——Evidencefrom the Posting Text of Eastmoney Stock Forum and the A-Share Market

doi:10.12005/orms.2022.0098

Operations Research and Management Science ›› 2022, Vol. 31 ›› Issue (3): 193-198.DOI: 10.12005/orms.2022.0098

• Application Research • Previous Articles Next Articles

The Design of Mean Reversion Strategy Considering Investor Sentiment Basedon Textual Information——Evidencefrom the Posting Text of Eastmoney Stock Forum and the A-Share Market

XU Wei-jun^1,2, PENG Zi-jin³, ZHANG Wei-guo^1,2, HUANG Jing-long¹

1. School of Business Administration, South China University of Technology, Guangzhou 510641, China;
2. Guangzhou Financial Services Innovation and Risk Management Research Base, Guangzhou 510641, China;
3. Planning & development Department, Guangzhou Baiyun International Airport Co., Ltd., Guangzhou 510405, China

Received:2020-04-21 Online:2022-03-25 Published:2022-04-12

基于文本信息考虑投资者情绪的均值回归策略设计——以东方财富股吧发帖文本和A股市场为例

徐维军^1,2, 彭子衿³, 张卫国^1,2, 黄静龙¹

1.华南理工大学工商管理学院, 广东广州 510641;
2.广州金融服务创新与风险管理研究基地,广东广州 510641;
3.广州白云国际机场股份有限公司规划发展部,广东广州 510405

通讯作者: 彭子衿(1993-),男,江西新余人,博士,研究方向:金融工程、投资规划。
作者简介:徐维军(1975-),男,宁夏固原人,教授,博士导师,研究方向:金融工程与风险管理;张卫国(1963-),男,陕西西康人,教授,博士导师,研究方向:金融工程与风险管理;黄静龙(1995-),女,山西运城人,硕士研究生,研究方向:金融工程与文本分析。
基金资助:
国家自然科学基金面上项目(71771091,71720107002);广东省基础与应用基础研究基金(2019A1515011752);科技部科技创新2030-“新一代人工智能”重大项目(2020AAA0108404)

Abstract

Abstract: In the current internet age, more and more text messages are becoming known. With the help of machine learning and other technical tools, it has been more convenient to mine information related to investor behavior and emotion from massive text data. Based on this, this paper explores the use of textual information to portray investor sentiment and refines a mean regression strategy that uses only price information. Using the text data such as the posting content in the Oriental Wealth stock bar to construct the investor sentiment index, combined with the characteristics of irrational investment behavior, we design a new weight transfer equation and obtain a new mean regression strategy. Finally,we use price and stock bar text data of some CSI 300 constituent stocks to conduct empirical tests on this strategy. The results show that the strategy considering investor sentiment proposed in this study has better income performance than the strategy describing the mean regression characteristics only using price information.

Key words: online portfolio, textual information, mean reversion, investor sentiment

摘要： 在当前互联网时代下,越来越多的文本信息为人们所认识。借助机器学习等技术工具,目前已能较为便捷地从海量的文本数据中挖掘出与投资者行为、情绪有关的信息。基于此,本研究探讨了利用文本信息刻画投资者情绪,并对仅利用价格信息的均值回归策略进行改进。利用东方财富股吧中发帖内容等文本数据构建投资者情绪指标,结合非理性投资行为的特征,设计新的权重转移方程,得到新的均值回归策略。最后,利用部分沪深300成分股的价格数据和股吧文本数据进行实证检验,结果表明:相比于仅利用价格信息刻画均值回归特征的策略,本研究提出的考虑投资者情绪的策略有更好的收益表现。

关键词: 在线投资组合, 均值回归, 投资者情绪, 文本信息

CLC Number:

F830.59

XU Wei-jun, PENG Zi-jin, ZHANG Wei-guo, HUANG Jing-long. The Design of Mean Reversion Strategy Considering Investor Sentiment Basedon Textual Information——Evidencefrom the Posting Text of Eastmoney Stock Forum and the A-Share Market[J]. Operations Research and Management Science, 2022, 31(3): 193-198.

徐维军, 彭子衿, 张卫国, 黄静龙. 基于文本信息考虑投资者情绪的均值回归策略设计——以东方财富股吧发帖文本和A股市场为例[J]. 运筹与管理, 2022, 31(3): 193-198.

References

[1] Markowitz H. Portfolio selection[J]. The Journal of Finance, 1952, 7(1): 77-91.
[2] 王灿杰,邓雪.基于可信性理论的均值-熵-偏度投资组合模型及其算法求解[J].运筹与管理,2019,28(2):154-159,192.
[3] 吴栩,李冉,燕汝贞,等.分形统计测度构建及其在投资组合中的应用研究[J].运筹与管理,2018,27(12):158-165.
[4] Cover T M. Universal portfolio[J]. Mathematical Finance, 1991, 1(1): 1-29.
[5] Borodin A, El-Yaniv R, Gogan V. Can we learn to beat the best stock[J]. Journal of Artificial Intelligence Research, 2004, 21(1): 579-594.
[6] DeBondt W, Thaler R. Does the stock market over react[J]. Journal of Finance, 1985, 40(3): 793-805.
[7] Jegadeesh N. Evidence of predictable behavior of security returns[J]. Journal of Finance, 1990, 45: 881-898.
[8] 宋玉臣,寇俊生.沪深股市均值回归的实证检验[J].金融研究,2006,(12):55-61.
[9] 李佳,王晓.中国股票市场有效性的实证研究——基于方差比的检验方法[J].经济经纬,2010,(1):137-140.
[10] Li B, Zhao P L, Hoi S C H. PAMR: Passive aggressive mean reversion strategy for portfolio selection[J]. Machine Learning, 2012, 87(2): 221-258.
[11] Li B, Hoi S C H, Sahoo D, et al. Moving average reversion strategy for on-line portfolio selection[J]. Artificial Intelligence, 2015, 222: 104-123.
[12] Tetlock P C. Giving content to investor sentiment: the role of media in the stock market[J]. Journal of Finance, 2007, 62(3): 1139-1168.
[13] Antweiler W, Frank M Z. Is all that talk just noise? the information content of internet stock message boards[J]. Journal of Finance, 2004, 59(3): 1259-1295.
[14] Blum A, Kalai A. Universal portfolios with and without transaction costs[J]. Machine Learning, 1999, 35(3): 193-205.
[15] Barker M, Wurgler J. Investor sentiment in stock market[J]. Journal of Economic Perspectives, 2007, 21(2): 129-151.
[16] Luo R X, Xu J J, Zhang Y, Ren X C, Sun X. PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation. Arxiv. 2019.
[17] Bagozzi R P, Dabholkar P A. Discursive psychology: an alternative conceptual foundation to means-end chain theory[J]. Psychology & Marketing, 2000, 17(7): 535-586.
[18] Nam K, Pyun C S, Kim S W. Is asymmetric mean-reverting pattern in stock returns systematic? evidence from pacific-basin markets in the short-horizon[J]. International Financial Markets Institutions & Money, 2003, 13(5): 481-502.

The Design of Mean Reversion Strategy Considering Investor Sentiment Basedon Textual Information——Evidencefrom the Posting Text of Eastmoney Stock Forum and the A-Share Market

基于文本信息考虑投资者情绪的均值回归策略设计——以东方财富股吧发帖文本和A股市场为例

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 7

Recommended Articles

Metrics

[1]	GAO Yang, SHEN Yi-ran, XU Jia-xi. Influence of Investor Sentiment on the Return Rate of Sci-Tech Innovation Board Based on Text Mining Perspective [J]. Operations Research and Management Science, 2022, 31(2): 184-190.
[2]	YANG Xing-yu, LIN Hong, HE Jin-an, ZHANG Yong. Online Portfolio Strategy Based on Order Prediction with Transaction Costs [J]. Operations Research and Management Science, 2021, 30(2): 168-175.
[3]	XIONG Xiong, LIU Mu-han, CHEN Shu-ning. Dynamic Characterization of the Influence of Investor Sentiment andMarket Rates of Interest on Stock Market Index Returns [J]. Operations Research and Management Science, 2018, 27(9): 156-169.
[4]	LUO Kan, WANG Chun-feng, FANG Zhen-ming. Social Interaction, Investor Sentiment Contagion and Asset Bubbles: An Empirical Study Based on the Stock Forum Discussion [J]. Operations Research and Management Science, 2018, 27(2): 124-132.
[5]	LUO Kan, WANG Chun-feng, FANG Zhen-ming. Study on Regime Switching of Capital Asset Pricing Model Considering Investor Sentiment: Based on the Emotion Analysis of the Stock Forum Discussion [J]. Operations Research and Management Science, 2017, 26(10): 129-136.
[6]	XIE Jun, GAO Bin. Market Equilibrium Analysis Based on Investor Sentiment [J]. Operations Research and Management Science, 2015, 24(6): 211-216.
[7]	JIA Li-na, HU Wen-xiu. Study on the Influence of Investor Sentiment on Fund Herding Effect [J]. Operations Research and Management Science, 2013, 22(6): 191-199.