CONSTRUCTION OF THE FLEXIBILITY INDEX FOR ARTIFICIAL INTELLIGENCE SYSTEMS IN THE CRYPTOCURRENCY MARKET
DOI:
https://doi.org/10.35774/Keywords:
artificial intelligence, cryptocurrency market, flexibility index, financial risks, adaptability, investment management, volatility.Abstract
Introduction. The problem of assessing the adaptability of intelligent trading systems in conditions of extreme volatility of the cryptocurrency market is becoming increasingly relevant. Traditional financial metrics have limitations when auditing artificial intelligence systems, since they are retrospective and do not take into account the ability of algorithms to respond to structural market fractures.
The purpose of the article is to develop methodological principles and a mathematical model of the index of flexibility of artificial intelligence systems for quantitative measurement of the ability of algorithms to self-regulate.
Results. The main result of the article is the division of the index into three functional components: the coefficient of adaptation speed, the coefficient of resistance to volatility and the coefficient of capital preservation under stressful conditions. A mathematical apparatus for normalizing indicators using a sigmoidal function is proposed, which allows reducing multidimensional data to a single scale. An information-functional architecture for calculating the index in real time has been developed, consisting of four sequential stages: data aggregation, anomaly detection, component calculation, and decision execution. In the course of the study, the concept of “AI flexibility” was conceptualized as the ability to autonomously identify changes in the market regime and dynamically change strategies.
Conclusions. The implementation of the index creates a basis for improving the quality of digital asset auditing and preventive risk management, allowing investors to identify “hard” models prone to overtraining. Further research will be aimed at empirically testing the model on historical crypto exchange data.
References
1. Dixon, M. F., Halperin, I., and Bilokon, P. (2020). Machine learning in finance: from theory to practice. Springer.
2. Mishchenko, S., Naumenkova, S., Tishchenko, Ye. (2025). Synerhiia shtuchnoho intelektu ta blokchein u finansovomu sektori [Synergy of artificial intelligence and blockchain in the financial sector]. Visnyk Kyivskoho natsionalnoho universytetu imeni Tarasa Shevchenka. Ekonomika – Bulletin of Taras Shevchenko National University of Kyiv. Economics, 2, 54–64. https://doi.org/10.17721/1728-2667.2025/227-2/7.
3. Mandych, O., Staverska, T., Malii, O. (2023). Intehratsiia shtuchnoho intelektu v rynok blokchein ta kryptovaliut [Integration of artificial intelligence into the blockchain and cryptocurrency market]. Modeling the Development of the Economic Systems, 4, 61–66. https://doi.org/10.31891/mdes/2023-10-8.
4. Moskalenko, V. V., Fonta, N. H., Havrylenko, A. V., Bezchastnyi, O. M. (2024). Analiz proble my prohnozuvannia trendiv kriptovaliutnoho rynku ta suchasni pidkhody do yii vyrishennia [Analysis of the problem of forecasting cryptocurrency market trends and modern approaches to its solution]. Visnyk Natsionalnoho tekhnichnoho universytetu “KhPI”. Stratehichne upravlinnia, upravlinnia portfeliamy, prohramamy ta proektamy – Bulletin of the National Technical University “KhPI”. Strategic management, portfolio, program and project management, 1, 41–49. https://doi.org/10.20998/2413-3000.2024.8.6.
5. Babych, O. (2025). Predicting cryptocurrency price movements using ai: integrating technical analysis and cyclical theories with machine learning models. International Humanitarian University Herald. Economics and Management, 62. https://doi.org/10.32782/2413-2675/2025-62-3.
6. Chyzhevska, M. B., Venher, V. V., Kushnirenko, O. M., Romanovska, N. I., Stepanenko, O. A. (2025). Prohnozuvannia tsiny kryptovaliut iz zastosuvanniam modeli FNN dlia optymizatsii investytsiinykh protsesiv [Forecasting cryptocurrency prices using the FNN model to optimize investment processes]. Yevropeiskyi naukovyi zhurnal ekonomichnykh ta finansovykh innovatsii – European Scientific Journal of Economic and Financial Innovations, 2, 36–50. https://doi.org/10.32750/2025-0204.
7. Koba, B. O., Polovenko, L. P. (2025). Statystychne doslidzhennia valiutnoi pary “ievro – dolar” z vykorystanniam shtuchnoho intelektu [Statistical study of the «euro – dollar» currency pair using artificial intelligence]. Visnyk Studentskoho naukovoho tovarystva DonNU imeni Vasylia Stusa – Bulletin of the Student Scientific Society of Vasyl Stus DonNU, 1, 176–181 [in Ukrainian].
8. Vankovych, L. Ya., Oberniienko, O. M., Perozhak, R. I., Steblii, O. I. (2026). Vykorystannia shtuchnoho intelektu u prohnozuvanni zovnishnotorhovealnykh potokiv [The use of artificial intelligence in forecasting foreign trade flows]. Stalyi rozvytok ekonomiky – Sustainable Development of Economy, 6, 537–542. https://doi.org/10.32782/2308-1988/2025-57-73.
9. Fang, F., Ventre, C., Basios, M., Kanthan, L., Martinez-Rego, D., Wu, F., and Li, L. (2025). Cryptocurrency trading: a comprehensive survey. Blockchain, crypto assets, and financial innovation. Singapore, 55–127. https://doi.org/10.1007/978-981-96-6839-7_4.
10. Bouri, E., Das, M., Gupta, R., and Roubaud, D. (2018). Spillovers between Bitcoin and other assets during bear and bull markets. Applied Economics, 50(55), 5935–5949.
11. Yermoshkina, O. V. (2025). Formuvannia kohnityvnykh uperedzhen na finansovomu rynku v umovakh rozvytku shtuchnoho intelektu [Formation of cognitive biases in the financial market in the conditions of artificial intelligence development]. Ekonomika, upravlinnia ta administruvannia – Economy, Management and Administration, 3, 111–118. https://doi.org/10.26642/ema-2025-3(113)-111-118.
12. Panasyuk, V. M. (2025). Shtuchnyi intelekt yak instrument pidvyshchennia efektyvnosti audytorskykh perevirok v Ukraini [Artificial intelligence as a tool for increasing the efficiency of audits in Ukraine]. Efektyvna ekonomika – Efficient Economy, 11. https://doi.org/10.32702/2307-2105.2025.11.4.
13. Zhong, X., Wei, J., Li, S., Xu, Q. (2024). Deep reinforcement learning for dynamic strategy interchange in financial markets. Applied Intelligence, 55(1). https://doi.org/10.1007/s10489-024-05965-2.
14. Hallensleben, S. (2025). AI Solution Quality Index (ASQI): A robust framework for procurement and deployment decisions. AI Assurance Forum: Blogs. Available at: https://resaro.ai/insights/articles/ai-solutions-quality-index-asqi-a-solid-basis-for-procurement-and-deployment-decisions.
15. Wedemeyer, M., Cramer, E., Mitsos, A., and Dahmen, M. (2026). Data-driven conditional flexibility index. Computers & Chemical Engineering, 211, 109647. Available at: https://doi.org/10.1016/j.compchemeng.2026.109647.
16. Park, S.-W., Zhang, Z., Li, F., and Son, S.- Y. (2021). Peer-to-peer trading-based efficient flexibility securing mechanism to support distribution system stability. Applied Energy, 285, 116403. https://doi.org/10.1016/j.apenergy.2020.116403.
