Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Li, Huiru | Hu, Yanrong; * | Liu, Hongjiu; *
Affiliations: School of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, China
Correspondence: [*] Corresponding author. Hongjiu Liu and Yanrong Hu, School of Mathematics and Computer Science, Zhejiang A&F University, Hangzhou, 311300, China. E-mail: [email protected]. (Hongjiu Liu); E-mail: [email protected]. (Yanrong Hu).
Abstract: Stock price volatility is influenced by many factors, including unstructured data that is not easy to quantify, such as investor sentiment. Therefore, given the difficulty of quantifying investor sentiment and the complexity of stock price, the paper proposes a novel LASSO-ATT-LSTM intelligent stock price prediction system based on multi-source data. Firstly, establish a sentiment dictionary in the financial field, conduct sentiment analysis on news information and comments according to the dictionary, calculate sentiment scores, and then obtain daily investor sentiment. Secondly, the LASSO (Least absolute shrinkage and selection operator) is used to reduce the dimension of basic trading indicators, valuation indicators, and technical indicators. The processed indicators and investor sentiment are used as the input of the prediction model. Finally, the LSTM (Long short-term memory) model that introduces the attention mechanism is used for intelligent prediction. The results show that the prediction of the proposed model is close to the real stock price, MAPE, RMSE, MAE and R2 are 0.0118, 0.0685, 0.0515 and 0.8460, respectively. Compared with the existing models, LASSO-ATT-LSTM has higher accuracy and is an effective method for stock price prediction.
Keywords: Stock price forecast, sentiment analysis, LSTM, attention, multi-source data
DOI: 10.3233/JIFS-221919
Journal: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 6, pp. 10511-10521, 2023
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
[email protected]
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office [email protected]
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
如果您在出版方面需要帮助或有任何建, 件至: [email protected]