Cybernetics And Systems Analysis logo
Editorial Board Announcements Abstracts Authors Archive
Cybernetics And Systems Analysis
International Theoretical Science Journal
-->

UDC 336.144.36, 519.216.3, 519.254
M. Kushnir1, K. Tokarieva2


1 Yu. Fedkovych National University, Chernivtsi, Ukraine

myk.kushnir@chnu.edu.ua

2 Yu. Fedkovych National University, Chernivtsi, Ukraine

tokarieva.chnu@gmail.com

A GENERALIZATION OF THE ARIMA MODEL TO THE NONLINEAR
AND CONTINUOUS CASES

Abstract. A method of extending the classical ARIMA and GARCH models to the continuous and nonlinear cases is considered. Stochastic functional differential equations, which are a natural generalization of the sums of independent random variables, are considered extended models. Along with the new model, a relevant optimization problem for estimating model parameters is considered, and the non-parametric problem is reduced to a parametric one. The new model was tested on real data, and the forecast results were compared with classical models.

Keywords: stochastic functional differential equations, genetic algorithm, forecasting of financial processes, stochastic optimization.


full text

REFERENCES

  1. Barro D., Consigli G., Varun V. A stochastic programming model for dynamic portfolio management with financial derivatives. Journal of Banking & Finance. 2022. Vol. 140. 106445. https://doi.org/10.1016/j.jbankfin.2022.106445.

  2. de Feo F., Federico S.,A. Optimal control of stochastic delay differential equations and applications to path-dependent financial and economic models. arXiv preprint arXiv:2302.08809. 17 Feb 2023. https://doi.org/10.48550/arXiv.2302.08809.

  3. Blechschmidt J. Numerical methods for stochastic control problems with applications in financial mathematics. Chemnitz Universiti of Technology, 2022. 223 p. URL: https://d-nb.info/1258447126/34.

  4. Mohammadi M., Rezakhah S., Modarresi N., Amindavar H. Continuous-time autoregressive models excited by semi-LБvy process for cyclostationary signal analysis. Digital Signal Processing. 2021. Vol. 118. P. 103–195. https://doi.org/10.1016/j.dsp.2021.103195.

  5. Atoev K.L., Knopov P.S., Pepelyaeva T.V. Development of new models for evaluating the effectiveness of nature management under conditions of climate change and growing uncertainty. Teoriya optymalʹnykh rishen'.2017. N 2017. P. 72–77.

  6. Knopova V.P., Pepelyaeva T.V. On some stochastic models of financial mathematics.Kibernetika i sistemnyj analiz. 2001. N 3. P. 152–158.

  7. Knopov P.S., Pepelyaeva T.V. About some trading strategies in the securities market. Kibernetika i sistemnyj analiz. 2002. N 5. P. 117–121.

  8. Costacurta J., Duncker L., Sheffer B., Williams A., Gillis W., Weinreb C., Markowitz J., Datta S., Linderman S. Distinguishing discrete and continuous behavioral variability using warped autoregressive HMMs. bioRxiv. June 28, 2022. https://doi.org/10.1101/2022.06.10.495690.

  9. Demchenko S.S., Knopov P.S., Chornei R.K. Optimal strategies for a semi-Markov inventory system. Kibernetika i sistemnyj analiz. 2002. N 1. P. 146–160.

  10. Pepelyaeva T.V. On the optimal moments for switching between securities portfolios. Kibernetika i sistemnyj analiz. 2002. N 1. P. 130–137.

  11. Pham Dinh-Tuan. Estimation of continuous-time autoregressive model from finely sampled data. IEEE Transactions on Signal Processing. 2020. Vol. 48, Iss. 9. P. 2576–2584. https://doi.org/10.1109/78.863060.

  12. Yang L., Gao T., Yubin L., Duan J., Liu T. Neural network stochastic differential equation models with applications to financial data forecasting. Applied Mathematical Modelling. 2023. Vol. 115. P. 279–299. https://doi.org/10.1016/j.apm.2022.11.001.

  13. Kennedy J., Eberhart R. Particle swarm optimization. Proc. of IEEE International Conference on Neural Networks. 1995. Vol. IV. P. 1942–1948.

  14. Kirshner H., Unser M., Ward J. On the unique identification of continuous-time autoregressive models from sampled data. Signal рrocessing. IEEE Transactions on Signal Processing. 2014. Vol. 62, Iss. 6. P. 1361–1376. https://doi.org/10.1109/TSP.2013.2296879.

  15. Ari Y. Continuous autoregressive moving average models: From discrete AR to LБvy–Driven CARMA models. In: Methodologies and Applications of Computational Statistics for Machine Intelligence. 2021. P. 118–141. https://doi.org/10.4018/978-1-7998-7701-1.ch007.

  16. Knopov P.S., Pepelyaeva T.V., Demchenko I.Yu. About one semi-Markov model of inventory management. Kibernetika i sistemnyj analiz. 2016. Vol. 52, N 5. P. 81–88.

  17. Norkin B.V. Stochastic method of successive approximations for assessing the risk of insolvency of an insurance company. Kibernetika i sistemnyj analiz. 2008. N 6. P. 116–130.

  18. Armillotta M., Fokianos K., Krikidis I. Bootstrapping network autoregressive Models for testing linearity. Data Science in Applications. 2023. P. 99–116. http://dx.doi.org/10.1007/ 978-3-031-24453-7_6.

  19. Brockwell P.J., Davis R.A. Introduction to time series and forecasting. 3rd ed. Springer, 2016. 425 p.

  20. Norkin B.V. Application of the method of successive approximations to find the probability of non-ruin of an insurance company in the presence of random premiums. Kibernetika i sistemnyj analiz. 2006. N 1. P. 112–127.




© 2023 Kibernetika.org. All rights reserved.