互联网时代下, 越来越多投资者开始在网络社区, 特别是在金融投资类社区中发表自己的投资观点与看法, 由此产生的海量金融文本数据具有较高的研究价值, 如何将这些金融文本数据加以利用已成为时下金融投资领域的研究热点。本文探究了如何将东方财富股吧中的投资者发帖文本转化为对应的情绪指标, 并基于此形成投资者意见, 在Black-Litterman模型框架下构建考虑金融文本情绪信息的投资组合模型。具体来讲, 首先利用网络爬虫从东方财富股吧中获取富时中国A50成分股对应的股吧发帖文本数据, 并进行数据预处理, 随后运用词典法和朴素贝叶斯法分别提取出股吧发帖文本的情绪指标;进一步将情绪指标、股票收盘价和成交量三项指标作为特征变量, 使用回归随机森林算法对股票的未来收益率进行预测;最后将预测得到的未来收益率作为投资者观点, 并置于Black-Litterman模型中构建考虑金融文本情绪信息的投资组合模型。回测结果显示, 使用朴素贝叶斯法构建的基于金融文本情绪挖掘的投资组合模型有更好的绩效表现。
In the Internet age, more and more investors are beginning to express their investment opinions in online communities, especially in financial investment communities. The resulting massive financial text data has high research value. How to apply these financial text data has become the current research hotspots in the field of financial investment. This article explores how to convert investor posts in the Eastmoney Stock Forum into corresponding sentiment indicators, and form investor opinions based on this, and builds a portfolio model that considers financial text sentiment information under the framework of the Black-Litterman model. Specifically, we first use web crawlers to crawl the post text data of FTSE China’s A50 constituent stocks from the Eastmoney Stock Forum, and perform data preprocessing. Then, the sentiment indicators of the post text is extracted by using the dictionary method and the Naive Bayes method. Furthermore, three indicators of sentiment index, stock closing price and trading volume are taken as characteristic variables, and the random forest regression algorithm is used to predict the future return rate of stocks. Finally, the predicted future return rate is taken as the investor’s point of view, and is put into the framework of Black-Litterman model to construct a new portfolio model considering the emotional information of financial text. The backtest results show that the financial text sentiment mining portfolio model based on the Naive Bayes method has better performance.
[1] Markowitz H. Portfolio selection[J]. Journal of Finance, 1952, 7(1): 77-91.
[2] Loomes G, Sugden R. Regret theory: An alternative theory of rational choice under uncertainty[J]. The Economic Journal, 1982, 92: 805-824.
[3] Bell D E. Disappointment in decision making under uncertainty[J]. Operations Research, 1985, 33(1): 1-27.
[4] 谢军, 杨春鹏, 闫伟. 含有无风险资产的情绪最优投资组合[J]. 系统管理学报, 2012, 21(04): 540-545.
[5] Black F, Litterman R. Global portfolio optimization[J]. Financial Analysts Journal, 1992, 48(5): 28-43.
[6] Bevan A, Winkelmann K. Using the Black-Litterman global asset allocation model: Three years of practical experience[R]. Goldman Sachs Fixed Income Research Paper, 1998: 1-19.
[7] He G, Litterman R. The intuition behind Black-Litterman model portfolios[EB/OL]. (2002-10-28)[2021-01-15]. https://ssrn.com/abstract=334304.
[8] Idzorek T. A step-by-step guide to the Black-Litterman model: Incorporating user-specified confidence levels[M]//Forecasting Expected Returns in the Financial Markets. Amsterdam: Elsevier, 2007: 17-38.
[9] Harris R D F, Stoja E, Tan L. The dynamic Black-Litterman approach to asset allocation[J]. European Journal of Operational Research, 2017, 259(3): 1085-1096.
[10] Kara M, Ulucan A, Atici K B. A hybrid approach for generating investor views in BlackLitterman model[J]. Expert Systems with Applications, 2019, 128(13): 256-270.
[11] Fang Y, Bo L, Zhao D, et al. Fuzzy views on Black-Litterman portfolio selection model[J]. Journal of Systems Science and Complexity, 2018, 31(4): 975-987.
[12] 方正, 程希骏, 葛颖. 基于多指标排序信息下Black-Litterman模型的研究[J]. 工程数学学报, 2015, 32(04): 517-523.
[13] 徐漫, 马晓微, 胡泽元. 基于Black-Litterman法的我国养老金组合管理研究[J]. 财政研究, 2016(4): 71-81.
[14] 姚加权, 张锟澎, 罗平. 金融学文本大数据挖掘方法与研究进展[J]. 经济学动态, 2020(4): 143-158.
[15] Nguyen T H, Shirai K, Velcin J. Sentiment analysis on social media for stock movement prediction[J]. Expert Systems with Applications, 2015, 42(24): 9603-9611.
[16] Sun Y, Fang M, Wang X, et al. GubaLex: Guba-oriented sentiment lexicon for big texts in finance[C]//2017 13th International Conference on Semantics, Knowledge and Grids (SKG). Beijing: IEEE, 2017: 25-32.
[17] Bollen J, Pepe A, Mao H. Modeling public mood and emotion: Twitter sentiment and socioeconomic phenomena[J]. Computer Science, 2009, 44(12): 2365-2370.
[18] 黄润鹏, 左文明, 毕凌燕. 基于微博情绪信息的股票市场预测[J]. 管理工程学报, 2015, 29(1): 47-52, 215.
[19] Wang Q, Xu W, Zheng H. Combining the wisdom of crowds and technical analysis for financial market prediction using deep random subspace ensembles[J]. Neurocomputing, 2018, 299: 51-61.
[20] Xing F Z, Cambria E, Welsch R E. Intelligent asset allocation via market sentiment views[J]. IEEE Computational Intelligence Magazine, 2018, 13(4): 25-34.
[21] Satchell S, Scowcroft A. A demystification of the Black-Litterman model: Managing quantitative and traditional portfolio construction[J]. Journal of Asset Management, 2000, 1(2): 138-150.
[22] Bian S, Jia D, Li F, et al. A new chinese financial sentiment dictionary for textual analysis in accounting and finance[EB/OL]. (2019-09-07)[2021-01-15]. https://ssrn.com/abstract=3446388.
[23] 周志华. 机器学习[M]. 北京:清华大学出版社, 2016.
[24] Breiman L. Random forests[J]. Machine Learning, 2001, 45(1): 5-32.
