Designing a hybrid model for stock marketing prediction based on LSTM and transfer learning

Document Type : Research Paper

Authors

1 Department of Information Technology Management, Faculty of Management and Accounting, Qazvin Branch, Islamic Azad University, Qazvin, Iran

2 Faculty of Electrical, Biomedical and Mechatronics Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

Abstract

One of the most complex and controversial issues in financial markets is the prediction of price and stock returns which is always a matter of interest to shareholders. The stock market is vulnerable to various factors that affect the price fluctuations in the stock market.  The development of a strong stock market algorithm that can accurately predict stock behaviour is important to maximize profits and minimize the loss of investors. Although in addition to the history of each share, other psychological factors affect the value of each share, in this research, an artificial intelligence model is proposed based on long short-term memory and text embedding. In addition to being paid to the stock market in the form of time series data; In order to investigate the psychological force of the market, features are also extracted from news sites. And finally, based on the combination of features extracted from news sites and time-series data, predicts the future of the stock market. The results of the evaluations show the proposed model can predict the market future truly.

Keywords

[1] K. Chourmouziadis and P.D. Chatzoglou, An intelligent short term stock trading fuzzy system for assisting investors in portfolio management, Expert Syst. Appl. 43(1) (2016) 298—311.
[2] P. Dattatray, K. Gandhmal and K. Kumar, Systematic analysis and review of stock market prediction techniques,
Comput. Sci. Rev. 34(1) (2019) 1–13.
[3] H. Ebrahimabad, KH. Jahangiri, H. Hasan Heydari and M. Ghaemi Asl, Study of shock and volatility spillovers
among selected indices of the Tehran Stock Exchange using asymmetric BEKK-GARCH model, Appl. Econ. Stud.
7(29) (2019) 123–155.
[4] A.V.C.I. Emin, Forecasting daily and sessional returns of the ISE-100 index with neural network models, Do˘gu¸s
Universitesi Dergisi 8(2) (2011) 128–142. ¨
[5] S. Feuerriegel and H. Prendinger, News-based trading strategies, Decision Support Syst. 90(1) (2021) 65–74.
[6] D. Katayama, Y. Kino and K. Tsuda, A method of sentiment polarity identification in financial news using deep
learning, Procedia Comput. Sci. 159(4) (2019) 1287—1294.
[7] H.Y. Kim and C.H. Won, Forecasting the volatility of stock price index: A hybrid model integrating LSTM with
multiple GARCH-type models, Expert Syst. Appl. 103(1) (2018) 25-–37.
[8] Y. Libo, Predicting the oil prices: Do technical indicators help?, Energ. Econ. 56(2) (2016) 338—350.
[9] Y. Liu, Q. Zeng, H. Yang and A. Carrio, Stock price movement prediction from financial news with deep learning
and knowledge graph embedding, In: K. Yoshida and M. Lee (eds) Knowledge Management and Acquisition for
Intelligent Systems, PKAW 2018, Lecture Notes in Computer Science, (2018) 102–113.
[10] R. Nau, Mathematical structure of ARIMA models, Duke University Online Article 1(1) (2014) 1–8.
[11] D. Oyewola, A. Ibrahim, J.A. Kwanamu and E Gbenga Dada, A new auditory algorithm in stock market prediction
on oil and gas sector in Nigerian stock exchange, Soft Comput. Lett. 3(1) (2021) 100013.[12] S.R. Polamuri, K. Srinivas and A.Krishna Mohan, Stock market prices prediction using random forest and extra
tree regression, Int. J. Recent Technol. Eng. 8(1) (2019) 1224–1228.
[13] R. Ramezanian, A. Peymanfar and B. Ebrahimi, An integrated framework of genetic network programming and
multi-layer perceptron neural network for prediction of daily stock return: An application in Tehran stock exchange
market, Appl. Soft Comput. J. 82(1) (2019) 1–16.
[14] R. Sutkatti and D.A. Torse, Stock market forecasting techniques: A survey, Int. Res. J. Eng. Technol. 48(42)
(2008) 4842—4844.
[15] S.N. Valinia, M.H. Ranjbar, H. Salari and D. Khodadady, Stock market reaction to real arnings management,
financial risk and business risk, Int. J. Nonlinear Anal. Appl. 13(1) (2022) 3347–3361.
[16] M. Vargas, B. Lima and A.G. Evsukoff, Deep learning for stock market prediction from financial news articles,
2017 IEEE Int. Conf. Comput. Intell. Virtual Environ. Meas. Syst. Appl. CIVEMSA (2017) 60–65.
[17] Z. Zhang, S. Zohren and S. Roberts, DeepLOB: Deep convolutional neural networks for limit order books, IEEE
Trans. Signal Process 67(11) (2019) 3001—3012.
Volume 12, Special Issue
December 2021
Pages 2325-2337
  • Receive Date: 20 October 2021
  • Revise Date: 29 November 2021
  • Accept Date: 12 December 2021