BUSINESS INFORM JOURNAL.

УКР

ENG

Search:

REGISTRATION CERTIFICATE

KV #19905-9705 PR dated 02.04.2013.

FOUNDERS

RESEARCH CENTRE FOR INDUSTRIAL DEVELOPMENT PROBLEMS of NAS of Ukraine (KHARKIV, UKRAINE)

ROR

EDRPOU 05481984

According to the decision No. 802 of the National Council of Television and Radio Broadcasting of Ukraine dated 14.03.2024, is registered as a subject in the field of print media.
ID R30-03156

PUBLISHER

Liburkina L. M.

CATALOG

A Comparative Analysis of Approaches to Modeling the Dynamics of the Cryptoasset Market
Merkulova T. V., Lutsenko R. R.

Merkulova, Tamara V., and Lutsenko, Rostyslav R. (2026) “A Comparative Analysis of Approaches to Modeling the Dynamics of the Cryptoasset Market.” Business Inform 3:314–325.
https://doi.org/10.32983/2222-4459-2026-3-314-325

Section: Economic and Mathematical Modeling

Article is written in Ukrainian
Downloads/views: 0

Download article (pdf) -

UDC 330.4

Abstract:
The article presents an analysis of statistical and algorithmic approaches to modeling, using machine learning methods and econometric analysis to model the dynamics of the cryptoasset market based on social media data. The relevance of the study is due to the high volatility of the cryptocurrency market and the need to use modern analytical tools to improve the accuracy of forecasting its development. The aim of the work is to explore the possibilities of combining multifactor regression models and machine learning methods to model changes in cryptoasset values. The main source of empirical data was behavioral metrics obtained via API from visually-oriented and social networks. The research methodology included the development of a system of quantitative indicators, their integration with financial time series, and comparative testing of different classes of models. Multifactor linear and polynomial models were built to describe the relationships between market indicators, and machine learning algorithms, in particular decision tree and random forest, were applied to model and forecast the dynamics of cryptoassets. A comparative analysis of the obtained results was carried out and the forecasting accuracy of different methods was evaluated. The results of the study indicate that the combination of statistical models and machine learning algorithms allows improving the quality of forecasting and provides a more comprehensive consideration of the complex nonlinear structure of the cryptocurrency market. The obtained results can be used for the further development of financial market forecasting methods and the improvement of tools for analytical support of investment decisions. Prospects for further research lie in the enhancement of models for processing visual content.

Keywords: dynamic models; econometric modeling; macro indicators; machine learning; market forecasting; cryptoasset market; social networks; behavioral factors; sentiment analysis.

Fig.: 7. Bibl.: 15.

Merkulova Tamara V. – Doctor of Sciences (Economics), Professor, Head of the Department, Department of Economic Cybernetics and Applied Economics, V. N. Karazin Kharkiv National University (4 Svobody Square, Kharkіv, 61022, Ukraine)
Email: [email protected]
Lutsenko Rostyslav R. – Associate Professor, Department of Economic Cybernetics and Applied Economics, V. N. Karazin Kharkiv National University (4 Svobody Square, Kharkіv, 61022, Ukraine)
Email: [email protected]

List of references in article

Baltakys K., Baltakiene M., Heidari N. & et al. (2023). Predicting the trading behavior of socially connected investors: Graph neural network approach with implications to market surveillance. Expert Systems with Applications, 228, 120285. https://doi.org/10.1016/j.eswa.2023.120285
Chaudhary D. & Saroj S. K. (2023). Cryptocurrency Price Prediction Using Machine Learning Algorithms. ADCAIJ: Advances in Distributed Computing and Artificial Intelligence Journal, 1(12), e31490. https://doi.org/10.14201/adcaij.31490
De B. (2023). API Management: An Architect’s Guide to Developing and Managing APIs for Your Organization. 2nd ed. Apress. https://doi.org/10.1007/979-8-8688-0054-2
Devlin J., Chang M.-W., Lee K. & Toutanova K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (pp. 4171–4186). https://doi.org/10.18653/v1/N19-1423
Gurgul V., Lessman S. & Hardle W. K. (2025). Deep Learning and NLP in Cryptocurrency Forecasting: Integrating Financial, Blockchain, and Social Media Data. International Journal of Forecasting, 4(41), 1666–1695. https://doi.org/10.1016/j.ijforecast.2025.02.007
Kahneman D. (2003). Maps of Bounded Rationality: Psychology for Behavioral Economics. The American Economic Review, 5(93), 1449–1475. https://doi.org/10.1257/000282803322655392
Kraaijeveld O. & De Smedt J. (2020). The predictive power of public Twitter sentiment for forecasting cryptocurrency prices. Journal of International Financial Markets, Institutions and Money, 65, 101188. https://doi.org/10.1016/j.intfin.2020.101188
Lutsenko R. R. (2024). Prykladnyi prohramnyi interfeis yak metod monitorynhu danykh sotsialnykh merezh dlia doslidzhen u povedinkovii ekonomitsi [Application programming interface as a method of monitoring social media data for research in behavioral economics]. Biznes Inform, 8, 133–141. https://doi.org/10.32983/2222-4459-2024-8-133-141
Lyons R. K. & Viswanath-Natraj G. (2023). What keeps stablecoins stable? Journal of International Money and Finance, 131, 102777. https://doi.org/10.1016/j.jimonfin.2022.102777
Murray K., Rossi A., Carraro D. & Visentin A. (2023). Cryptocurrency Price Prediction: A Comparison of Machine Learning, Deep Learning, and Ensembles. Forecasting, 1(5), 196–209. https://doi.org/10.3390/forecast5010010
Raviv L., Meyer A. & Lev-Ari S. (2020). The Role of Social Network Structure in the Emergence of Linguistic Structure. Cognitive Science, 8(44), e12876. https://doi.org/10.1111/cogs.12876
Sundarasen S. & Saleem F. (2025). From Tweets to Trades: A Bibliometric and Systematic Review of Social Media’s Influence on Cryptocurrency. International Journal of Financial Studies, 2(13), 87. https://doi.org/10.3390/ijfs13020087
Tanwar S., Patel N. P., Patel S. N. & et al. (2021). Deep Learning-Based Cryptocurrency Price Prediction Scheme with Inter-Dependent Relations. IEEE Access, 9, 1–15. https://doi.org/10.1109/ACCESS.2021.3117848
Thaler R. H. (2017). Misbehaving: The Making of Behavioral Economics. The Review of Austrian Economics, 30, 137–141. https://doi.org/10.1007/s11138-015-0330-z
Zhang C., Li W., Zhang H. & Zhan T. (2024). Recent Advances in Intelligent Data Analysis and Its Applications. Electronics, 1(13), 226. https://doi.org/10.3390/electronics13010226