Risk Estimation in the Bitcoin Market Using a Three-Stage Ensemble Method

Accurate risk estimation formulates the essential foundation of risk management in the Bitcoin market. A new three-stage ensemble method is introduced to solve the inherent instability of single models when estimating Bitcoin risk. In the proposed method, single models are first employed to estimate risk using a training dataset. Second, a model selection process based on the difference between actual and expected failure rates is introduced to categorize these single models into overestimating and underestimating types. Finally, a new weighting ensemble model based on the expected failure rates is utilized to estimate the Bitcoin risk. Empirical results demonstrate that the ensemble model employing the new model selection method outperforms these single models across 5% Value at risk (VaR) estimation under three distinct weighting schemes. Moreover, through the application of the model selection method, only the ensemble model utilizing the new weighting approach successfully passes the VaR backtesting under all three confidence levels. These findings indicate the potential of the proposed three-stage ensemble method as a promising solution for Bitcoin risk estimation.