Borisenko G.A. NEURAL NETWORKS TO FORECAST STOCK PRICES BASED ON NEWS DATA

The Bulletin of the Institute of Economics of the Russian Academy of Sciences № 5/2024. Finance.

Georgiy A. Borisenko

Postgraduate student, Faculty of Economics, Lomonosov Moscow State University, Moscow, Russia

ORCID: 0009-0000-8430-7744

NEURAL NETWORKS TO FORECAST STOCK PRICES BASED ON NEWS DATA

211-232

594.08 KB

Full text

Abstract

This work is devoted to forecasting the movement of the stock prices of large Russian companies represented in the Moscow Exchange Index, based on news data. Transformer neural networks as well as classical machine learning are used as forecast models. Large Russian news sources and Telegram channels on economics and finance concerns are used as news data. The problem is solved in two settings: classification into 2 classes (the share price will be higher/lower than the current one) and classification into 3 classes (the share price will be higher/approximately at the same level/lower than the current one). As a result of the study, it was found that classical machine learning methods cope better with this task in the general case, but neural networks also show good quality for large companies.

Keywords: stock price, news, neural networks.

JEL: С63, G14

EDN: KJVYKJ

DOI: https://doi.org/10.52180/2073-6487_ 2024_5_211_232

References

Kuznetsov R.S., Tumarova T.G. Forecasting stock prices of PJSC Gazprom using LSTM neural networks // Bulletin of the Institute of Economics of the Russian Academy of Sciences. 2023. No. 3. Pp. 84–98. DOI: 10.52180/2073-6487_2023_3_84_98. (In Russ.).
Biau G., Scornet E. A random forest guided tour // Test. 2016. Vol. 25. Pp. 197–227. DOI: 1007/s11749-016-0481-7.
De Fortuny E.J. et al. Evaluating and understanding text-based stock price prediction models // Information Processing & Management. 2014. Vol. 50. No. 2. Pp. 426–441. DOI: 10.1016/j.ipm.2013.12.002.
Fama E.F. Efficient capital markets // Journal of finance. 1970. Vol. 25. No. 2. Рp. 383–417. DOI: 10.2307/2325486.
Gidofalvi G., Elkan C. Using news articles to predict stock price movements // Department of computer science and engineering, university of California. San Diego. 2001. Vol. 17. DOI: 10.1109/IJCNN.2018.8489208.
Li Y., Pan Y. A novel ensemble deep learning model for stock prediction based on stock prices and news // International Journal of Data Science and Analytics. 2022. Pp. 1–11. DOI: 10.1007/s41060-021-00279-9.
Liu J. et al. Transformer-based capsule network for stock movement prediction // Proceedings of the First Workshop on Financial Technology and Natural Language Processing. 2019. Pp. 66–73. DOI: 10.1016/j.eswa.2022.117239.
Mittal A., Goel A. Stock prediction using twitter sentiment analysis // Standford University, CS229. 2012. Vol. 15. P. 2352.
Natekin A., Knoll A. Gradient boosting machines, a tutorial // Frontiers in neurorobotics. 2013. Vol. 7. P. 21. DOI: 10.3389/fnbot.2013.00021.
Sekioka S., Hatano R., Nishiyama H. Market prediction using machine learning based on social media specific features // Artificial Life and Robotics. 2023. Vol. 28. No. 2. 410–417. DOI: 10.1007/s10015-023-00857-z.
Vaswani A. et al. Attention is all you need // Advances in neural information processing systems. 2017. Vol. 30. DOI: 10.48550/arXiv.1706.03762.
Volodin S.N., Kuranov G.M., Yakubov A.P. Impact of Political News: Evidence from Russia // Scientific Annals of Economics and Business. 2017. Vol. 64. No. 3. Pp. 271–287. DOI: 10.1515/saeb-2017-0018.
Xu Y., Cohen S. B. Stock movement prediction from tweets and historical prices // Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers). 2018. Pp. 1970–1979. DOI: 10.18653/v1/P18-1183.
Zhang J., Ye L., Lai Y. Stock price prediction using CNN-BiLSTM-Attention model // Mathematics. 2023. Vol. 11. No. 9. P. 1985. DOI: 10.3390/math11091985.

Manuscript submission date: 12.09.2024

For citation:

Borisenko G.A. Neural networks to forecast stock prices based on news data // Vestnik Instituta Ekonomiki Rossiyskoy Akademii Nauk. 2024. № 5. Pp. 211-232. (In Russ.). https://doi.org/10.52180/2073-6487_ 2024_5_211_232 EDN: KJVYKJ

Creative Commons 4.0