Abstract
The theoretical foundations of the GARCH-model to be applied for calculating financial risk have been considered. The article discusses the AI neural network for assessing financial risk conditioned by the time series volatility using the GARH method in order to reduce it during exchange trading.
There has been suggested and proven a hypothesis that the Kohonen map neural network enables forecasting the extent of loss on price volatility of the SiU8 futures contract, as well as forecasting the price of a financial instrument, which is important for successful trading.
The relevance is due to the fact that in the conditions of a “turbulent” economy, an increase in the price volatility of the USD futures contract is observed on the exchange market, with the application of artificial intelligence systems being important for forecasting financial risk by the AI GARCH model.
Assessing the extent of loss on financial volatility risk is of great importance in the contest of market uncertainty. The dynamics of changes in assets is known to have periods of high and low volatility. The neural networks that make it possible to predict the loss both on the risk of volatility and the SiU8 futures contract prices have been successfully developed.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Basegroup Advanced analytics without programming. https://basegroup.ru/deductor/description. Accessed 13 Sept 2019
VAR calculation based on GARCH model (1,1). http://abnsecurities.blogspot.com/2018/02/var-garch11.html. Accessed 13 Sept 2019
Autoregressive conditional heteroscedasticity. https://ru.wikipedia.org/wiki/. Accessed 12 Sept 2019
Lomakin, N.I., Grishankin, A.I., Maksimova, O.N.: Exchange operations with the company’s securities as a tool to reduce financial risks. In: The Interaction Between Enterprises and Universities: Science, Personnel and Innovation: Coll. of Reports of IX Interregional Scientific-Practical Conference, Volzhsky, 18–19 April 2013, VPI (branch) VSTU, Volgograd, 1 CD-ROM, pp. 174–177 (2013)
GARCH(1,1) Analysis. http://investexcel.net. Accessed 10 Sept 2019
Kohonen self-organizing map (2019). https://ru.wikipedia.org/wiki/. Accessed 10 Sept 2019
James, D., Raul, S.: Autoregressive conditional heteroskedasticity and changes in regime. J. Econom. 64(1–2), 307–333 (1994)
Bing, C., Robinson, P.: Semiparametric estimation from time series with long-range dependence. J. Econom. 64(1–2), 335–353 (1994)
Blundell, R., Smith, R.: Coherency and estimation in simultaneous models with censored or qualitative dependent variables. J. Econom. 64(1–2), 355–373 (1994)
Danielsson, J.: Stochastic volatility in asset prices estimation with simulated maximum likelihood. J. Econom. 64(1–2), 375–400 (1994)
Lomakin, N., Kopylov, A., Lomakina, A., Lomakin, I., Gorbunova, A., Maximov, O., Moskovtsev, A., Sazonov, S., Drobotova, O., Lukyanov, G.: Certificate of registration of a computer program, no. 2018611017, dated January 22, 2018. Russian Federation. Neural Network is a perceptron for price forecast USD/RUB/VSTU (2018)
Acknowledgments
The article was funded by the Russian Foundation for Basic Research “Cognitive approach to theoretical and methodological foundations of strategic development of small businesses in the digital economy system taking drift risks into account” No. 18-010-01210 - A.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lomakin, N.I., Petrukhin, A.V., Shokhnekh, A.V., Telyatnikova, V.S., Meshcheryakova, Y.V. (2020). AI for Assessing Financial Risk Conditioned by the Time-Series Volatility Using the GARCH-Method. In: Popkova, E., Sergi, B. (eds) Artificial Intelligence: Anthropogenic Nature vs. Social Origin. ISC Conference - Volgograd 2020. Advances in Intelligent Systems and Computing, vol 1100. Springer, Cham. https://doi.org/10.1007/978-3-030-39319-9_83
Download citation
DOI: https://doi.org/10.1007/978-3-030-39319-9_83
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-39318-2
Online ISBN: 978-3-030-39319-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)