Economic Efficiency of Implementing Flexible Artificial Intelligence Systems in the Digitalization of Big Data in the Cryptocurrency Market
DOI:
https://doi.org/10.58423/2786-6742/2025-11-44-57Keywords:
digital transformation, economic efficiency, cryptocurrency, artificial intelligence, big data, financial markets, crypto marketAbstract
The rapid development of the cryptocurrency market and the growing volumes of big data necessitate the implementation of flexible artificial intelligence systems in order to enhance the economic efficiency of analytical, forecasting, and risk management processes. Under conditions of high volatility, information asymmetry, and increasing requirements for data processing speed, the use of intelligent algorithms becomes a key determinant of the competitiveness of cryptocurrency market participants. This underscores the scientific and practical relevance of investigating the economic efficiency of applying flexible artificial intelligence systems to the digitalisation of big data in the cryptocurrency market. The purpose of the work is to identify the main determinants of AI flexibility, assess their impact on the processes of price analysis and forecasting in the cryptocurrency segment of financial markets, as well as substantiate the possibilities of integrating such systems into corporate strategies of companies. The subject of the study is the flexibility of artificial intelligence (AI) in the process of processing big data in the cryptocurrency market, which is considered one of the key factors in increasing the efficiency of algorithmic trading and analytical systems in a highly volatile environment. The flexibility of AI is interpreted as its ability to adapt to rapidly changing market conditions, which determines the effectiveness of forecasting and making management decisions. The research methodology is based on the application of comparative and systemic analysis of modern digital technologies, in particular machine learning and neural networks, as well as on modeling forecast scenarios using linear regression and machine learning algorithms. The work takes into account both theoretical developments in the field of financial technologies and practical examples of implementing AI for algorithmic trading in the cryptocurrency market.
The results of the study demonstrate that the flexibility of AI is due to a combination of several factors: the ability of algorithms to automatically update and self-learn; the integration of various types of data sources, including information flows from social media and news resources; ensuring fast interaction between humans and machines, which accelerates the decision-making process; and taking into account cybersecurity aspects that are critically important for the stability of digital platforms. It was found that it is the presence of adaptation mechanisms that allows you to increase the accuracy of forecasts and minimize the risks associated with market volatility.
The scope of application of the results covers the practice of algorithmic trading, the development of analytical systems for forecasting price trends, the formation of corporate strategies in the cryptocurrency market, as well as educational programs in financial technologies and the digital economy. The conclusions obtained can be used by both analysts and traders, and managers of enterprises that integrate innovative digital technologies into their activities.
The conclusions emphasize that the effectiveness of AI in the cryptocurrency market depends on a comprehensive consideration of the determinants of its flexibility, among which the adaptability of algorithms and data protection occupy a leading place. The use of AI not only optimizes forecasting and trading processes, but also opens up new opportunities for business development in the context of digital transformation. The combination of technological innovations with a systemic approach to risk management forms the basis for increasing the competitiveness of companies in the field of financial technologies.
References
1. Brechko, O. V. (2023). Development of DeFi and Web3 in the context of digital transformation. Ekonomichnyi dyskurs, (3–4), 95–109. https://doi.org/10.36742/2410-0919-2023-2-1 [in Ukrainian]
2. Derbentsev, V., Matviychuk, A., & Solovyov, V. (2020). Cryptocurrency price forecasting using machine learning. In L. Pikhl, K. Eom, E. Skalas, & T. Kaydzodzi (Eds.), Advanced research in financial technologies and cryptocurrency markets (pp. 211–231). Springer Singapore. https://doi.org/10.1007/978-981-15-4498-9_12 [in English]
3. Kleban, Yu., & Stasyuk, T. (2022). Cryptocurrency price forecasting: Prospects of neural networks. Visnyk Natsionalnoho banku Ukrainy, 254, 29–42. https://doi.org/10.26531/vnbu2022.254.03 [in Ukrainian]
4. Nikolenko, D. (2021). Machine learning and decision-making. Bukhhalterski ta finansovi doslidzhennia, 10(3), 1–12. https://doi.org/10.5430/afr.v10n3p1 [in Ukrainian]
5. Kuchkovskyi, V. V. (2022). Blockchain information technologies for big data processing (Candidate’s thesis). National University “Lviv Polytechnic”, Lviv, Ukraine. [in Ukrainian]
6. Danilov, V., & Oliynyk, B. (2022). Forecasting stock prices using neural networks. InterConf Grafiati, 14(113), 479–485. http://dx.doi.org/10.51582/interconf.19-20.06.2022.051 [in Ukrainian]
7. Didyk, A. M., & Nechay, O. R. (2024). Comparative analysis of the formation and development of cryptocurrencies in the world: Lessons for Ukraine. Visnyk Skhidnoukrainskoho natsionalnoho universytetu imeni Volodymyra Dalya, (3), 112–118. [in Ukrainian]
8. Hlushchenko, O. V., Shvayko, M. L., Khmelkov, A. V., & Danylkyna, O. I. (2023). Modern trends in the cryptocurrency market in Ukraine. Zbirnyk naukovykh prats Kharkivskoho natsionalnoho universytetu imeni V. N. Karazina, (18), 59–65. [in Ukrainian]
9. Nechay, O. (Ed.). (2024). Concepts, types and prospects of cryptocurrency use in Ukraine. Modeliuvannia rozvytku ekonomichnykh system, (2), 23–29. [in Ukrainian]
10. Wu, J., Zhang, X., Huang, F., Zhou, H., & Chandra, R. (2024). Review of deep learning models for crypto price prediction: implementation and evaluation. ArXiv, abs/2405.11431. https://doi.org/10.48550/arXiv.2405.11431
11. Sonh, K. H., Den, L., Van, K. H., et al. (2025). Deep learning-based time series forecasting. Artificial Intelligence Review, 58, 23. https://doi.org/10.1007/s10462-024-10989-8 [in English]
12. Guo, Q., Lei, S., Ye, Q., & Fang Z. (2021). MRC-LSTM: Hibrydnyy pidkhid bahatomasshtabnoyi zalyshkovoyi CNN ta LSTM dlya prohnozuvannya tsiny Bitcoin. https://arxiv.org/abs/2105.00707 (2021) [in English]
13. Cohen, G., & Aiche, A. (2025). Predicting the Bitcoin's price using AI. Frontiers in artificial intelligence, 8, 1519805. https://doi.org/10.3389/frai.2025.1519805
14. CoinMarketCap. (n.d.). Cryptocurrency market capitalization. https://coinmarketcap.com [in English]
15. McKinsey & Company. (n.d.). The state of AI: How organizations are transforming to capture value. https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai [in English]
16. McKinsey & Company. (2024). The state of AI in early 2024: Next-generation AI adoption is accelerating and beginning to generate value. https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-state-of-ai-2024 [in English]
17. McKinsey & Company. (n.d.). The next innovation revolution - enabled by AI. https://www.mckinsey.com/capabilities/quantumblack/our-insights/the-next-innovation-revolution-pow [in English]
18. Two Sigma Investments. (n.d.). Using artificial intelligence and machine learning in algorithmic trading. https://www.twosigma.com/ [in English]
19. CryptoHedge. (n.d.). A platform for cryptocurrency price forecasting using neural networks. https://www.cryptohopper.com [in English]
20. CoinPredictor. (n.d.). A service for forecasting and analyzing the cryptocurrency market using artificial intelligence. https://coinpredictor.live/ [in English]
21. Numerai. (n.d.). A hedge fund using artificial intelligence and crowdsourcing for algorithmic trading. https://www.numer.ai/ [in English]
22. Chainalysis. (n.d.). A platform for blockchain data analysis and financial crime investigation. https://www.chainalysis.com/ [in English]
23. Elliptic. (n.d.). Blockchain analytics and compliance solutions for cryptocurrency transactions. https://www.elliptic.co/ [in English]
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Oleksandr Brechko, Vadim Schuchmann

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons CC BY-NC License.
