3035. Integrating energy-related risks in Bitcoin’s price
Invited abstract in session MA-9: Innovation in Insurance and Financial Risk Management, stream OR in Finance and Insurance .
Monday, 8:30-10:00Room: Clarendon SR 2.01
Authors (first author is the speaker)
| 1. | Rosella Castellano
|
| Law and Economics, University of Rome, Unitelma Sapienza |
Abstract
Bitcoin, the world’s leading cryptocurrency, exhibits substantial return volatility and an energy-intensive mining process, raising concerns about energy costs, sustainability, and environmental policies among investors and policymakers. This study explores the interactions between Bitcoin price dynamics, energy prices, and network metrics through a hybrid approach combining GARCH(1,1) econometric modeling and advanced machine learning techniques like Random Forest and XGBoost. Using a comprehensive dataset of Bitcoin log returns, energy prices, and network activity, the analysis highlights the critical role of temporal aggregation. Shorter aggregation periods fail to capture meaningful relationships due to the mismatch between daily energy prices and miners' fixed monthly rates. Conversely, monthly aggregations reveal robust medium-term dependencies, with energy prices and network hash rate emerging as key drivers of Bitcoin volatility. Explainability tools such as Shapley values and partial dependence plots allow us to explore the role of energy consumption and costs in shaping Bitcoin’s market dynamics and emphasize the nonlinear response of volatility to energy price fluctuations, providing a deeper understanding of energy-related risks in the cryptocurrency market. This work helps regulators and stakeholders understand the level of integration of cryptocurrency markets within the global financial system.
Keywords
- Machine Learning
- Financial Modelling
- Forecasting
Status: accepted
Back to the list of papers