Forecasting the dynamics of the exchange rate using econometric methods and artificial neural networks.
https://doi.org/10.34020/2073-6495-2023-4-094-108
Abstract
The article presents the possibilities of applying the methods of applied statistics used in modern analysis to analyze the dynamics of the exchange rate. The exchange rate in the modern world is quite a significant tool of the economic system of the state. Determining the trend in the development of the exchange rate is important in almost any business direction that involves capital investment. In modern economic conditions, it has a rather differential character, which is accompanied by risk, to one degree or another. And although assets in US dollars have declined in recent years, the Central Bank did not plan to completely abandon the dollar in its reserves, since this currency is necessary to maintain financial stability, given the high role of the US currency in foreign trade settlements and its fundamental role in financial flows. To predict the dynamics of the exchange rate, the official US dollar exchange rate was taken. Methods of constructing predictive models using ARIMA models and prediction models based on neural networks are proposed for making forecasts. The models were evaluated and the most accurate variant was proposed – a model based on the construction of neural networks (MLP model 12-8-1 (No. 4)) with a prediction error of 6 %.
About the Authors
L. P. Bakumenko
Mari State University
Russian Federation
Russian Federation
Bakumenko Lyudmila P., Doctor of Economic Sciences, Professor, Head of the Department of Applied Statistics and Digital Technologies
Yoshkar-Ola
I. A. Lipatova
Mari State University
Russian Federation
Russian Federation
Lipatova Irina A., Master, Department of Applied Statistics and Digital Technologies
Yoshkar-Ola
References
1. Belotelova N.P. Valjutnaja sistema i mezhdunarodnye valjutno-kreditnye otnoshenija: monografija [Monetary system and international monetary relations: monograph]. Moscow, Nauchnyj konsul’tant, 2017. 94 p.
2. Bukreeva A.S. Perspektivy povyshenija statusa rossijskogo rublja do mezhdunarodnoj rezervnoj valjuty [Prospects for raising the status of the Russian ruble to an international reserve currency], Ustojchivoe razvitie nauki i obrazovanija [Sustainable development of science and education], 2021, no. 10 (61), pp. 30–34. EDN EODDXU.
3. Zarova E.V., Zarov I.K. Nejronnye seti kak sredstvo modelirovanija i prognozirovanija infljacionnyh processov [Neural networks as a means of modeling and forecasting inflation processes], Vestnik Samarskogo gosudarstvennogo tehnicheskogo universiteta. Serija Fiziko-matematicheskie nauki [Bulletin of the Samara State Technical University. Series Physical and Mathematical Sciences], 2005, no. 34, pp. 182–186.
4. Zenkina E.V. Mezhdunarodnye valjutno-finansovye otnoshenija v postindustrial’nom mire: monografija [International monetary and financial relations in the post-industrial world: monograph]. Moscow, INFRA-M, 2018. 169 p.
5. Kozadaev A.S. Predvaritel’naja ocenka kachestva obuchajushhej vyborki dlja iskusstvennyh nejronnyh setej v zadachah prognozirovanija vremennyh rjadov [Preliminary assessment of the quality of the training sample for artificial neural networks in time series forecasting problems], Vestn. Tamb. un-ta. Ser. Estestv. i tehn. nauki [Vestn. Tamb. Univ. Ser. Natural and tech. science], 2008, vol. 13, iss. 1, p. 100.
6. Aminian F., Suarez E.D., Aminian M., Walz D.T. Forecasting economic data with neural networks. Computational Economics, 2006, vol. 28, issue 1, pp. 71–88.
7. Catik A.N., Karaçuka M. A comparative analysis of alternative univariate time series models in forecasting Turkish inflation. Journal of Business Economics and Management, 2012, vol. 13, issue 2, pp. 275–293.
8. Godovoj otchet Banka Rossii za 2021 god [Annual report of the Bank of Russia for 2021]. [Electronic resource]. Available at: https://cbr.ru/Collection/Collection/File/40915/ar_2021.pdf (accessed: 27.12.2022).
9. Edinaja mezhvedomstvennaja informacionno-statisticheskaja sistema (EMISS) [Unified Interdepartmental Information and Statistical System (EMISS)]. [Electronic resource]. Available at: https://www.fedstat.ru/ (accessed: 20.08.2023).
10. Mel’nik M.S. Instrumenty srochnogo valjutnogo rossijskogo rynka na jetape sovremennogo razvitija [Instruments of the Russian fixed-term currency market at the stage of modern development], Nauka i obrazovanie segodnja [Science and education today], 2020, no. 2 (49). Available at: https://cyberleninka.ru/article/n/instrumenty-srochnogovalyutnogo-rossiyskogo-rynka-na-etape-sovremennogo-razvitiya (accessed: 10.01.2023).
11. Obzor dejatel’nosti Banka Rossii po upravleniju aktivami v inostrannyh valjutah i zolote [Review of the activities of the Bank of Russia on asset management in foreign currencies and gold], 2022, no. 1 (61). [Electronic resource]. Available at: https://www.cbr.ru/Collection/Collection/File/39684/2022-01_res.pdf (accessed: 20.08.2023).
12. RBK Jekonomika [RBC Economics]. [Electronic resource]. Available at: https://www.rbc.ru/economics/23/07/2021/60faa84e9a7947c072b8caa3 (accessed: 09.08.2023).
13. Central’nyj bank Rossijskoj Federacii [Central Bank of the Russian Federation]. [Electronic resource]. Available at: https://cbr.ru/ (accessed: 29.05.2023).
14. «Statistical forecasting: notes on regression and time series analysis» Robert Nau, Introduction to ARIMA: nonseasonal models. [Electronic resource]. Available at: https://people.duke.edu/~rnau/411seart.htm (accessed: 29.08.2023).
Review
For citations:
Bakumenko L.P., Lipatova I.A. Forecasting the dynamics of the exchange rate using econometric methods and artificial neural networks. Vestnik NSUEM. 2023;(4):94-108. (In Russ.) https://doi.org/10.34020/2073-6495-2023-4-094-108
Email this article 
