Application of Predictive Models in Bitcoin Forecasting and Risk Management
DOI:
https://doi.org/10.15611/pn.2026.3.05Keywords:
predictive model, Stock-to-Flow (S2F) model, BitcoinAbstract
Aim: The aim of the article was to assess the statistical relevance of the Stock-to-Flow (S2F) model in forecasting the value of Bitcoin by 2030 and its usefulness in risk management.
Methodology: A method based on quantitative analysis of the Stock-to-Flow (S2F) model was used. Bitcoin price data and the corresponding S2F values between 2009 and 2025 were collected, formatted and cleaned of redundant information. Then a predictive model in the form of logarithmic-linear regression was defined. In the next step, a statistical price was made of the degree of matching the model with the data. Finally, specific forecast values were determined and potential turning points in price cycles were identified.
Results: The results of quantitative analysis based on the Stock-to-Flow (S2F) model indicate a strong statistical relationship between Bitcoin's rarity and its market price over the period under review. The S2F model, despite its limitations considering only the supply side, apart from rapid changes on the demand side, showed a high predictive capacity for medium-term trends and allowed for the identification of market phases, making it a useful instrument in the process of reducing investment risk.
Implications and recommendations: The stock-to-flow model is a tool to help assess Bitcoin's long-term supply dynamics and the role of halving cycles as a deflationary mechanism. In the context of risk management in financial markets it offers a useful timeframe to identify cyclical patterns and support allocation decisions over a multi-year horizon. To increase the effectiveness of risk management it should be a hybrid element with other on-chain metrics (e.g. the number of new network users, their purchase price) or risk measures such as Value at Risk (VaR).
Originality/value: The use of cryptocurrencies and predictive models in risk management in financial markets has shown measurable benefits resulting from their use. The potential of medium-term models to predict future values and assess their usefulness in an effective investment risk management strategy in the maturing cryptocurrency market was estimated.
Downloads
References
Bergsli, L. Ø., Lind, A. F., Molnár, P., & Polasik, M. (2022). Forecasting Volatility of Bitcoin. Research in International Business and Finance, 59, 101540. https://doi.org/10.1016/j.ribaf.2021.101540
Box, G. E. P., Jenkins, G. M., Reinsel, G. C., & Ljung, G. M. (2015). Time Series Analysis: Forecasting and Control (5th ed.). Wiley.
Changchit, C., Cutshall, R., Pham, L., & Bland, E. (2025). Psychological and Technological Factors Shaping Cryptocurrency Investment: The Moderating Role of Personality Traits. Acta Psychologica, 260, 105606. https://doi.org/10.1016/j.actpsy.2025.105606
Dixon, M. F., Halperin, I., & Bilokon, P. (2020). Machine Learning in Finance: From Theory to Practice. Springer. https://doi.org/10.1007/978-3-030-41068-1
Hull, J. C. (2023). Risk Management and Financial Institutions (6th ed.). Wiley.
Katsiampa, P. (2017). Volatility Estimation for Bitcoin: A Comparison of GARCH Models. Economics Letters, 158, 3-6. https://doi.org/10.1016/j.econlet.2017.06.023
Kristoufek, L. (2015). What Are the Main Drivers of the Bitcoin Price? Evidence from Wavelet Coherence Analysis. PLOS ONE, 10(4), E0123923. https://doi.org/10.1371/journal.pone.0123923
Kyriazis, N. A. (2020). Herding Behaviour in Digital Currency Markets: An Integrated Survey and Empirical Estimation. Heliyon, 6(8), e04752. https://doi.org/10.1016/j.heliyon.2020.e04752
Lee, K., & Jeong, D. (2023). Too Much Is Too Bad: The Effect of Media Coverage on the Price Volatility of Cryptocurrencies. Journal of International Money and Finance, 133, 102823. https://doi.org/10.1016/j.jimonfin.2023.102823
M’bakob, G. B. (2024). Bubbles in Bitcoin and Ethereum: The Role of Halving in the Formation of Super Cycles. Sustainable Futures, 7, 100178. https://doi.org/10.1016/j.sftr.2024.100178
Morillon, T. G., & Chacon, R. G. (2022). Dissecting the Stock-to-Flow Model for Bitcoin. Studies in Economics and Finance, 39(3), 506-523. https://doi.org/10.1108/SEF-10-2021-0409
Nakamoto, S. (2008). Bitcoin: A Peer-to-Peer Electronic Cash System. Bitcoin. Retrieved August 31, 2026, from https://bitcoin.org/bitcoin.pdf
Omole, O., & Enke, D. (2024). Deep Learning for Bitcoin Price Direction Prediction: Models and Trading Strategies Empirically Compared. Financial Innovation, 10, 117. https://doi.org/10.1186/s40854-024-00643-1
PlanB. (2019). Modeling Bitcoin’s Value with Scarcity. Medium. Retrieved August 31, 2026, from https://medium.com/@100trillionUSD/modeling-bitcoins-value-with-scarcity-91fa0fc03e25
Shahbazi, Z., & Byun, Y.-C. (2022). Machine Learning-Based Analysis of Cryptocurrency Market Financial Risk Management. IEEE Access, 10, 37848-37856. https://doi.org/10.1109/ACCESS.2022.3162858
Shelton, A. (2024). Bitcoin Return Prediction: Is It Possible via Stock-to-Flow, Metcalfe’s Law, Technical Analysis, or Market Sentiment? Journal of Risk and Financial Management, 17(10), 443. https://doi.org/10.3390/jrfm17100443
Wątorek, M., Drożdż, S., Kwapień, J., Minati, L., Oświęcimka, P., & Stanuszek, M. (2021). Multiscale Characteristics of the Emerging Global Cryptocurrency Market. Physics Reports, 901, 182. https://doi.org/10.1016/j.physrep.2020.10.005
Zahid, M., Iqbal, F., & Koutmos, D. (2022). Forecasting Bitcoin Volatility Using Hybrid GARCH Models with Machine Learning. Risks, 10(12), 237. https://doi.org/10.3390/risks10120237
Downloads
Published
License
Copyright (c) 2026 Beata Butryn, Kamil Lupa
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Accepted 2026-07-30
Published 2026-10-07
