Predicting value at risk for cryptocurrencies with generalized random forests

We study the prediction of value at risk (VaR) for cryptocurrencies. In contrast to classic assets, returns of cryptocurrencies are often highly volatile and characterized by large fluctuations around single events. Analyzing a comprehensive set of 105 major cryptocurrencies, we show that generalized random forests (GRF) adapted to quantile prediction have superior performance over other established methods such as quantile regression, GARCH-type models, and CAViaR models. This advantage is especially pronounced in unstable times and for classes of highly volatile cryptocurrencies. Furthermore, we identify important predictors during such times and show their influence on forecasting over time. Moreover, a comprehensive simulation study indicates that the GRF methodology is at least on par with existing methods in VaR predictions for standard types of financial returns, and clearly superior in the cryptocurrency setup.