融合情感分析和GAN-TrellisNet的股价预测方法

doi:10.3778/j.issn.1002-8331.2306-0418

摘要/Abstract

摘要： 将时序深度神经网络应用于股票价格预测，已成为量化金融领域的重要研究方向。时序神经网络具有很好的序列数据捕捉能力和学习记忆能力，在股票预测上有一定适用性。但是现有的模型大多存在预测准确度不高、模型结构复杂导致训练时间较长等问题. 为了解决以上问题，提出了一种基于情感分析和GAN-TrellisNet的股价预测方法。提出了一个基于LSTM-CNN的情感分析模型，用于分析爬虫获取的主流金融论坛股票评论，并获得股票情感指数。为了提高预测准确度，将情感指数和百度搜索指数加入股票交易数据中作为训练集，提出了一个基于TrellisNet和CNN的改进型GAN股价预测模型，利用TrellisNet生成器的卷积特性来捕捉数据的局部特征，选取特征提取能力较强的CNN作为判别器来区别预测结果和真实股价。通过选取10只代表性股票和三种大盘指数的不同时段数据进行算法验证，结果表明，与ConvLSTM和GAN-LSTM预测模型相比，GAN-TrellisNet模型能有效缩短训练时间，提高预测准确率。

关键词: 量化金融, 股价预测, 情感分析, 百度指数, 生成对抗网络, TrellisNet

Abstract: Applying time series neural networks to stock price prediction, has become one of the important applications in the quantitative finance field. Time sequence neural networks have excellent ability to capture sequence data and learning memory, and have certain applicability in stock prediction. However, most existing models have problems such as low prediction accuracy and long training time due to complex model structures. In order to solve these problems, a stock prediction method based on sentiment analysis and GAN-TrellisNet is proposed. Firstly, a sentiment analysis model based on LSTM-CNN is proposed to analyze stock comments obtained from financial forums crawled by spiders, and obtain stock sentiment index. In order to improve prediction accuracy, the sentiment index and Baidu search index are added to the stock trading data as the training set. An improved GAN stock price prediction model based on TrellisNet and CNN is proposed, using the convolution characteristics of the TrellisNet generator to capture the local features of the data, and selecting CNN with strong feature extraction ability as a discriminator to distinguish between predicted results and real stock prices. The algorithm is verified by selecting data from 10 representative stocks and 3 stock indices in different periods. The result shows that compared with ConvLSTM and GAN-LSTM prediction models, the GAN-TrellisNet model can effectively shorten training time and improve prediction accuracy.

Key words: quantitative finance, stock price prediction, sentiment analysis, Baidu index, generative adversarial network(GAN), TrellisNet

葛业波, 刘文杰, 顾雨晨. 融合情感分析和GAN-TrellisNet的股价预测方法[J]. 计算机工程与应用, 2024, 60(12): 314-324.

GE Yebo, LIU Wenjie, GU Yuchen. Stock Price Prediction Method by Fusing Sentiment Analysis and GAN-TrellisNet[J]. Computer Engineering and Applications, 2024, 60(12): 314-324.

参考文献

[1] ABDUL-RAHMAN S, MUTALIB S. Mining textual terms for stock market prediction analysis using financial news[C]//Proceedings of International Conference on Soft Computing in Data Science. Singapore: Springer, 2017: 293-305.
[2] BINKOWSKI M, MARTI G, DONNAT P. Autoregressive convolutional neural networks for asynchronous time series[C]//Proceedings of International Conference on Machine Learning, 2018: 580-589.
[3] MEHTAB S, SEN J. Stock price prediction using convolutional neural networks on a multivariate timeseries[EB/OL]. (2020-01-10) [2023-06-20]. https://arxiv.org/abs/2001.09769.
[4] MEHTAB S, SEN J, DUTTA A. Stock price prediction using machine learning and LSTM-based deep learning models[C]//Proceedings of Symposium on Machine Learning and Metaheuristics Algorithms, and Applications. Singapore: Springer, 2020: 88-106.
[5] SEN J, DUTTA A, MEHTAB S. Profitability analysis in stock investment using an LSTM-based deep learning model[C]//Proceedings of the 2nd International Conference for Emerging Technology (INCET). Belagavi: IEEE, 2021: 1-9.
[6] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, Cambridge, 2014: 2672-2680.
[7] KONG J, KIM J, BAE J. Hifi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis[C]//Advances in Neural Information Processing Systems, 2020: 17022-17033.
[8] ISOLA P, ZHU J Y, ZHOU T, et al. Image-to-image translation with conditional adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, Hawaii, 2017: 1125-1134.
[9] XIONG W, LUO W, MA L, et al. Learning to generate time-lapse videos using multi-stage dynamic generative adversarial networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 2018: 2364-2373.
[10] VONDRICK C, PIRSIAVASH H, TORRALBA A. Generating videos with scene dynamics[C]//Advances in Neural Information Processing Systems, 2016: 613-621.
[11] DENG S M, ZHANG N Y, ZHANG W, et al. Knowledge-driven stock trend prediction and explanation via temporal convolutional network[C]//Companion Proceedings of The 2019 World Wide Web Conference, San Francisco, 2019: 678-685.
[12] DUARTE J J, MONTENEGRO GONZáLEZ S, CRUZ J C. Predicting stock price falls using news data: evidence from the Brazilian market[J]. Computational Economics, 2021, 57(1): 311-340.
[13] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[EB/OL]. (2020-01-16) [2023-06-21]. https://arxiv.org/abs/1301.3781.
[14] BAI S, KOLTER J Z, KOLTUN V. Trellis networks for sequence modeling[EB/OL]. (2018-09-27) [2023-06-20]. https://arxiv.org/abs/1810.06682.
[15] 吴玉霞, 温欣. 基于ARIMA模型的短期股票价格预测[J]. 统计与决策, 2016(23): 83-86.
WU Y X, WEN X. Short-term stock price prediction based on ARIMA model[J]. Statistics and Decision, 2016(23): 83-86.
[16] DADHICH M, PAHWA M S, JAIN V, et al. Predictive models for stock market index using stochastic time series ARIMA modeling in emerging economy[M]//Advances in mechanical engineering. Singapore: Springer, 2021: 281-290.
[17] ZHANG G P. Time series forecasting using a hybrid ARIMA and neural network model[J]. Neurocomputing, 2003, 50: 159-175.
[18] CHEN K, ZHOU Y, DAI F Y. A LSTM-based method for stock returns prediction: a case study of China stock market [C]//Proceedings of IEEE International Conference on Big Data. CA: Santa Clara, 2015: 2823-2824.
[19] 邹婕, 李路. RF-SA-GRU模型的股价预测研究[J]. 计算机工程与应用, 2023, 59 (15): 300-309.
ZOU J, LI L. Stock price prediction research based on RF-SA-GRU model[J]. Computer Engineering and Applications, 2023, 59 (15): 300-309.
[20] FARAZ M, KHALOOZADEH H. Multi-step-ahead stock market prediction based on least squares generative adversarial network[C]//Proceedings of the 28th Iranian Conference on Electrical Engineering (ICEE). Tabriz: IEEE, 2020: 1-6.
[21] ZHOU X Y, PAN Z S, HU G Y. et al. Stock market prediction on high-frequency data using generative adversarial nets[J]. Mathematical Problems in Engineering, 2018: 4907423.
[22] GILBERT E, KARAHALIOS K. Widespread worry and the stock market[C]//Proceedings of the International AAAI Conference on Web and Social Media, 2010 : 58-65.
[23] CAROSIA A E D O, COELHO G P, SILVAA E A D. Investment strategies applied to the Brazilian stock market: a methodology based on sentiment analysis with deep learning[J]. Expert Systems with Applications, 2021, 184: 115470.
[24] 田红丽, 金硕, 闫会强. 一种基于TCN和新闻情感的股票预测方法[J]. 信息技术与信息化, 2021(6): 17-21.
TIAN H L, JIN S, YAN H Q. A stock prediction method based on TCN and news sentiment[J]. Information Technology & Informatization, 2021(6): 17-21.
[25] 刘玉玲, 赵国龙, 邹自然, 等. 基于情感分析和GAN的股票价格预测方法[J]. 湖南大学学报 (自然科学版), 2022, 49(10): 111-118.
LIU Y L, ZHAO G L, ZOU Z R, et al. Stock price prediction method based on sentiment analysis and generative adversarial network[J]. Journal of Hunan University (Natural Sciences), 2022, 49(10): 111-118.
[26] 林培光, 周佳倩, 温玉莲. SCONV: 一种基于情感分析的金融市场趋势预测方法[J]. 计算机研究与发展, 2020, 57(8): 1769-1778.
LIN P G, ZHOU J Q, WEN Y L. SCONV: a financial market trend forecast method based on emotional analysis[J]. Journal of Computer Research and Development, 2020, 57(8): 1769-1778.