UDC 004.89
The article considers the problem of decision support in financial markets under conditions of non-stationarity and high volatility, typical for the Russian market during the period of increased macroeconomic uncertainty in 2022–2024. Traditional approaches based on technical analysis with fixed parameters lose effectiveness during abrupt changes in market regimes. A method for dynamically adapting the calculation periods of technical indicators based on a power-law dependence on current market volatility is proposed, ensuring a nonlinear response of the system to changing market conditions. The architecture of the hybrid LSTM-TI-Adaptive model is developed, integrating 33 input features (28 adaptive technical indicators and 5 basic OHLCV features) with a two-layer LSTM recurrent neural network. The proposed method automatically configures the parameters of all indicator classes—trend indicators, oscillators, volume indicators, and volatility indicators—based on a single adaptation mechanism, eliminating manual intervention. The proposed method's effectiveness has been confirmed by experimental testing on 28 financial instruments from the Russian, American, and cryptocurrency markets for the period 2015–2024: the adaptive architecture provides a 4.2 percentage point increase in average annual returns and a 3.1 percentage point decrease in maximum drawdown compared to a system with fixed parameters, confirming the practical significance of the developed adaptation method.
decision support systems, non-stationary time series, adaptive systems, system analysis, architecture of information systems, decision-making methods, deep learning, experimental research
1. Opiola M., Souza M.H., Souza M., de Nuccio E. The role of artificial intelligence for management decision-making: a structured literature review // Management Decision. 2023. Vol. 61. No. 13. P. 1–29.
2. Power D.J., Sharda R., Burstein F. Decision Support Systems // Wiley Encyclopedia of Management. 2015. Vol. 7. P. 1–4. DOI:https://doi.org/10.1002/9781118785317.weom070211
3. Murphy J. Technical Analysis of Futures Markets: Theory and Practice / translated from English. Moscow: Diagramma, 2020. 592 p.
4. Glebova A.G., Kovaleva A.A. Forecasting Volatility of the Russian Stock Market under International Economic Sanctions // Finance: Theory and Practice. 2024. Vol. 28. No. 1. Pp. 20–29. DOI:https://doi.org/10.26794/2587-5671-2024-28-1-20-29
5. Vortelinos D.I. Forecasting Realized Volatility: HAR vs. Principal Components Combining, Neural Networks, and GARCH // Research in International Business and Finance. 2017. Vol. 39. Pp. 824–839. DOI:https://doi.org/10.1016/j.ribaf.2015.01.004
6. Vidmant O.S. Forecasting Financial Time Series Using LSTM Recurrent Neural Networks // Society: Politics, Economics, Law. 2018. No. 5. Pp. 63–66.
7. Alzheev A.V., Kochkarov R.A. Comparative Analysis of ARIMA and LSTM Forecasting Models Using Russian Company Stocks as an Example // Finance: Theory and Practice. 2020. Vol. 24. No. 1. Pp. 14–23. DOI:https://doi.org/10.26794/2587-5671-2020-24-1-14-23
8. Savin S.V., Murzin A.D. Decision Support Systems Based on Artificial Intelligence: Integration, Adaptation, and Performance Assessment // Economics and Management. 2024. Vol. 30. No. 12. Pp. 1521–1534.
9. Borovykh A., Bohte S., Oosterlee C.W. Conditional time series forecasting with convolutional neural networks // Expert Systems with Applications. 2022. Vol. 186. Article 115742.
10. Livieris I.E., Kiriakidou N., Stavroyiannis S., Pintelas P. An advanced deep learning model for short-term forecasting US natural gas price and movement // Energy. 2024. Vol. 257.
11. Sezer O.B., Gudelek M.U., Ozbayoglu A.M. Financial time series forecasting with deep learning: A systematic literature review: 2005–2019 // Applied Soft Computing. 2020. Vol. 90. Article 106181. DOI:https://doi.org/10.1016/j.asoc.2020.106181
12. Jiang W. Applications of deep learning in stock market prediction: Recent progress // Expert Systems with Applications. 2021. Vol. 184. Article 115537. DOI:https://doi.org/10.1016/j.eswa.2021.115537
13. Fischer T., Krauss C. Deep learning with long short-term memory networks for financial market predictions // European Journal of Operational Research. 2018. Vol. 270. No. 2. P. 654–669. DOI:https://doi.org/10.1016/j.ejor.2017.11.054
14. Lim B., Arik S.O., Loeff N., Pfister T. Temporal fusion transformers for interpretable multi-horizon time series forecasting // International Journal of Forecasting. 2021. Vol. 37.No. 4. P. 1748–1764. DOI:https://doi.org/10.1016/j.ijforecast.2021.03.012
15. Nabipour M., Nayyeri P., Jabani H., Mosavi A., Salwana E. Deep learning for stock market prediction // Entropy. 2020. Vol. 22.No. 8. Article 840. DOI:https://doi.org/10.3390/e22080840
