融合投资者情绪的S_AM_BiLSTM股价预测模型

doi:10.3778/j.issn.1002-8331.2305-0059

摘要/Abstract

摘要： 股票价格预测一直是金融领域的研究热点之一。然而，股票价格的形成机制是相当复杂的，各种因素都可能会导致股票价格的变化。为此，提出了一种基于深度学习方法并融合多源数据和投资者情绪的股票价格预测混合模型（S_AM_BiLSTM）。利用文本卷积神经网络（TextCNN）对从股票论坛中提取的投资者评论进行情绪分析，并计算情绪指数。将情绪指数（sentiment）、技术指标和股票历史交易数据作为股价预测模型的特征集，采用双向长短时记忆神经网络（BiLSTM）对股票的收盘价进行预测，并在此基础上加入注意力机制（attention mechanism），提高预测精度。为了证明模型的有效性和适用性，随机选取4个重点行业的股票进行实证研究。实验结果表明，与其他单一模型和不含情绪因子的模型相比，所提出的混合模型的效果更优越。

关键词: 深度学习, 双向长短期记忆网络（BiLSTM）, 文本卷积神经网络（TextCNN）, 股价预测, 情绪分析

Abstract: Stock price forecasting has always been one of the research hotspots in the financial field. However, the formation mechanism of stock price is quite complex, and various factors may lead to the change of stock price. Therefore, this paper proposes a hybrid model of stock price forecasting based on deep learning method and integrating multi-source data and investor sentiment (S_AM_BiLSTM). First, it uses the TextCNN to analyze the sentiment of investor comments extracted from stock forums, and calculates the emotional factors. Then, taking emotional factors, technical indicators and stock historical trading data as the feature set of stock price prediction, the bi-directional long short-term memory neural network is used to predict the stock closing price, and on this basis, attention mechanism is added to improve the prediction accuracy. In order to prove the validity and applicability of the model, it randomly selects four key industries for empirical research. The experimental results show that the proposed hybrid model is more effective than other single models and models without emotional factors.

Key words: deep learning, bi-directional long short-term memory (BiLSTM), TextCNN, stock price prediction, sentiment analysis

袁婧, 潘甦, 谢浩, 徐文鹏. 融合投资者情绪的S_AM_BiLSTM股价预测模型[J]. 计算机工程与应用, 2024, 60(7): 274-281.

YUAN Jing, PAN Su, XIE Hao, XU Wenpeng. Stock Price Prediction Integrating Investor Sentiment Based on S_AM_BiLSTM Model[J]. Computer Engineering and Applications, 2024, 60(7): 274-281.

参考文献

[1] BADEA L, IONESCU V, GUZUN A. What is the causal relationship between STOXX EUROPE 600 sectors? but between large firms and small firms?[J]. Economic Computation and Economic Cybernetics Studies and Research, 2019, 53(3): 5-20.
[2] JIN Z, YANG Y, LIU Y. Stock closing price prediction based on sentiment analysis and LSTM[J]. ?Neural Computing and Applications, 2020, 32: 9713-9729.
[3] NEILD S. A review of time-frequency methods for structural vibration analysis[J]. Engineering Structures, 2003, 25(6): 713-728.
[4] KRUNZ M, MAKOWSKI A. Modeling video traffic using M/G//splinfin/ input processes: a compromise between Markovian and LRD models[J]. IEEE Journal on Selected Areas in Communications, 2002, 16(5): 733-748.
[5] FARINA L, RINALDI S. Positive linear systems: theory and applications[M]. [S.l.]: Wiley, 2000.
[6] CONTRERAS J, ESPINOLA R, NOGALES F J, et al. ARIMA models to predict next-day electricity prices[J]. ?IEEE Transactions on Power Systems, 2003, 18(3): 1014-1020.
[7] DEISENROTH M P, RASMUSSEN C E, PETERS J. Gaussian process dynamic programming[J]. Neurocomputing, 2009, 72(7/8/9): 1508-1524.
[8] JIANG W. Applications of deep learning in stock market prediction: recent progress[J]. Expert Systems with Applications, 2021, 184: 115537.
[9] 黄建华, 钟敏, 胡庆春. 基于改进粒子群算法的LSTM股票预测模型[J]. 华东理工大学学报, 2022, 48(5): 696-707.
HUANG J H, ZHONG M, HU Q C. LSTM stock prediction model based on improved particle swarm optimization algorithm[J]. Journal of East China University of Technology, 2022, 48(5): 696-707.
[10] LU W J, LI J Z, WANG J Y, et al. A CNN-BiLSTM-AM method for stock price prediction[J]. Neural Computing and Applications, 2021, 33: 4741-4753.
[11] KAZEM A, SHARIFI E, HUSSAIN F K, et al. Support vector regression with chaos-based firefly algorithm for stock market price forecasting[J]. Applied Soft Computing, 2013, 13(2): 947-958.
[12] BAKER M, WURGLER J. Investor sentiment and the cross‐section of stock returns[J]. The Journal of Finance, 2006, 61(4): 1645-1680.
[13] BAKER M, WURGLER J. Investor sentiment in the stock market[J]. Journal of Economic Perspectives, 2007, 21(2): 129-151.
[14] PAGOLU V S, CHALLA K, PANDA G, et al. Sentiment analysis of Twitter data for predicting stock market movements[C]//2016 International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES), Paralakhemundi, India, 2016: 1345-1350.
[15] DE FORTUNY E J, DE SMEDT T, MARTENS D, et al. Evaluating and understanding text-based stock price prediction models[J]. Information Processing & Management, 2014, 50(2): 426-441.
[16] 包振山, 郭俊南, 谢源, 等. 基于LSTM-GA的股票价格涨跌预测模型[J]. 计算机科学, 2020, 47(S1): 467-473.
BAO Z S, GUO J N, XIE Y, et al. Model for stock price trend prediction based on LSTM and GA[J]. Computer Science, 2020, 47(S1): 467-473.
[17] SWATHI T, KASIVISWANATH N, RAO A A. An optimal deep learning-based LSTM for stock price prediction using twitter sentiment analysis[J]. Applied Intelligence, 2022, 52: 13675-13688.
[18] HUANG C J, LIAO J J, YANG D X, et al. Realization of a news dissemination agent based on weighted association rules and text mining techniques[J]. Expert Systems with Applications, 2010, 37(9): 6409-6413.
[19] 张泽亚, 黄丽明, 陈翀, 等. 基于新闻特征抽取和循环神经网络的股票预测方法[J]. 文献与数据学报, 2020, 2(1): 45-56.
ZHANG Z Y, HUANG L M, CHEN C, et al. Stock prediction method based on news feature extraction and convolutional neural network[J]. Journal of Literature and Data, 2020, 2(1): 45-56.
[20] FRIESEN G, WELLER P A. Quantifying cognitive biases in analyst earnings forecasts[J]. Journal of Financial Markets, 2006, 9(4): 333-365.
[21] QIN P, XU W, GUO J. A novel negative sampling based on TFIDF for learning word representation[J]. Journal of Neurocomputing, 2015, 177(12): 257-265.
[22] BRA?INSKAS A, HAVRYLOV S, TITOV I. Embedding words as distributions with a Bayesian skip-gram model[J]. arXiv:1711.11027, 2017.
[23] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems, 2013: 3111-3119.
[24] KIM Y. Convolutional neural networks for sentence classification[J]. arXiv:1408.5882, 2014.
[25] ANTWEILER W, FRANK M Z. Is all that talk just noise? The information content of internet stock message boards[J]. The Journal of Finance, 2004, 59: 1259-1294.