Financial news effect analysis on stock price prediction using a stacked LSTM model

• Autorzy: Heiden Alexandre , Parpinelli Rafael Stubs

Identyfikatory

DOI

10.15439/2022F20

• Konferencja: 17th Conference on Computer Science and Intelligence Systems
• Języki publikacji: EN

Abstrakty

EN

In the age of information, it is understood that social media provides valuable reference for many contexts, including the financial market. Although having high volume, publications on social media are not necessarily reliable. In this context, this research aims to examine the influence of financial news coming from a more transparent source, the newspaper The New York Times. This source provides fact-checked news, but the volume of information is lower compared to social media. The strategy proposes a difficult challenge, the application of a Machine Learning model on a limited dataset. The LSTM-based stock price prediction model proposed has two features, news sentiment and historical data of the assets. Experiments indicate that the model performs better when the news' sentiments are considered and demonstrates potential to accurately predict stock prices up to around 35 days into the future, comparing the results obtained with the real prices on the period.

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 32
• Strony: 233--240
• Opis fizyczny: Bibliogr. 16 poz., rys., tab., wykr.

Twórcy

autor

Heiden Alexandre

• Santa Catarina State University Graduate Program in Applied Computing Joinville, SC – Brazil

autor

Parpinelli Rafael Stubs

• Santa Catarina State University Graduate Program in Applied Computing Joinville, SC – Brazil

Bibliografia

• 1. E. F. Fama, “Efficient Capital Markets: II”, The journal of finance, vol. 46, 1991, pp. 1575-1617.
• 2. K. Liagkouras, K. Metaxiotis, “Efficient Portfolio Construction with the Use of Multiobjective Evolutionary Algorithms: Best Practices and Performance Metrics”, International Journal of Information Technology & Decision Making, vol. 14, 2015, pp. 535-564, http://dx.doi.org/10.1142/S0219622015300013.
• 3. C. Hutto, E. Gilbert, “VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text”, International AAAI Conference on Web and Social Media, vol. 8, 2014.
• 4. R. Schumaker, H. Chen. “Textual Analysis of Stock Market Prediction Using Financial News Articles”, AMCIS Proceedings, 2006, p. 185.
• 5. M. Roondiwala, H. Patel, S. Varma, “Predicting Stock Prices Using LSTM”, International Journal of Science and Research (IJSR), vol. 6, 2017, pp. 1754-1756.
• 6. F. A. Gers, J. Schmidhuber, F. Cummins, “Learning to Forget: Continual Prediction with LSTM”, Neural Computation, vol. 12, 2000, pp. 2451-2471, http://dx.doi.org/10.1162/089976600300015015.
• 7. K. Adam, A. Marcet, J. P. Nicolini, “Stock Market Volatility and Learning”, The Journal of Finance, vol. 71, 2016, pp 33-82, http://dx.doi.org/10.1111/jofi.12364.
• 8. M. Rana, M. M. Uddin, M. M. Mhoque. “Effects of Activation Functions and Optimizers on Stock Price Prediction Using LSTM Recurrent Networks”, International Conference on Computer Science and Artificial Intelligence, vol. 3, 2019, pp. 354-358, http://dx.doi.org/10.1145/3374587.3374622.
• 9. X. Du, K. Tanaka-Ishii, “Stock Embeddings Acquired From News Articles and Price History, and an Application to Portfolio Optimization”, Annual Meeting of the Association for Computational Linguistics, vol. 58, 2020, pp. 3353-3363, http://dx.doi.org/10.18653/v1/2020.acl-main.307.
• 10. H. Markowitz, “Portfolio Selection”, The Journal of Finance, vol. 7, 1952, pp. 77-91.
• 11. F. Xing, D. H. Hoang, D.-V. Vo, “High-frequency News Sentiment and its Application to Forex Market Prediction”, Hawaii International Conference on System Sciences, vol. 54, 2020.
• 12. H. Maqsood et al. “A Local and Global Event Sentiment Based Efficient Stock Exchange Forecasting Using Deep Learning”, International Journal of Information Management, vol. 50, 2020, pp. 432-451, http://dx.doi.org/10.1016/j.ijinfomgt.2019.07.011.
• 13. P. Patil, C. S. M. Wu, K. Potika, M. Orang, “Stock Market Prediction Using Ensemble of Graph Theory, Machine Learning and Deep Learning Models”, International Conference on Software Engineering and Information Management, vol. 3, 2020, pp. 85-92, http://dx.doi.org/10.1145/3378936.3378972.
• 14. Z. Jin, Y. Yang, Y. Liu, “Stock Closing Price Prediction Based on Sentiment Analysis and LSTM”, Neural Computing and Applications, vol. 32, 2020, pp. 9713-9729, http://dx.doi.org/10.1007/s00521-019-04504-2.
• 15. R. Cheng, J. Gao. “On Cardinality Constrained Mean-CVaR Portfolio Optimization”, 27th Chinese Control and Decision Conference, 2015, p. 1074-1079, http://dx.doi.org/10.1109/CCDC.2015.7162076.
• 16. A. Heiden, R. Parpinelli. “Applying LSTM for Stock Price Prediction with Sentiment Analysis”, 15th Brazilian Congress of Computational Intelligence, 2021, p. 1-8, http://dx.doi.org/10.21528/CBIC2021-45.

Uwagi

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).