Risk of Bitcoin Market: Volatility, Jumps, and Forecasts

TL;DR

This paper investigates Bitcoin market risk by analyzing volatility, jumps, and forecasting models, revealing that jumps significantly impact future risk and that modeling jumps benefits long-term variance predictions.

Contribution

It provides a comprehensive analysis of Bitcoin's risk dynamics, emphasizing the importance of jumps and realized volatility in forecasting models.

Findings

Lagged realized variance predicts future variance.

Positive jumps reduce future realized variance.

Explicit jump modeling improves long-term variance forecasts.

Abstract

Cryptocurrency, the most controversial and simultaneously the most interesting asset, has attracted many investors and speculators in recent years. The visibly significant market capitalization of cryptos also motivates modern financial instruments such as futures and options. Those will depend on the dynamics, volatility, or even the jumps of cryptos. We provide a comprehensive investigation of the risk dynamics of the Bitcoin Market from a realized volatility perspective. The Bitcoin market is extremely risky in the sense of volatility, entangled jumps, and extensive consecutive jumps, which reflect the major incidents worldwide. Empirical study shows that the lagged realized variance increases the future realized variance, while the jumps, especially positive ones, significantly reduce future realized variance. The out-of-sample forecasting model reveals that, in terms of forecasting accuracy and utility gain, investors interested in the long-term realized variance benefit from explicitly modelling the jumps and signed estimators, which is unnecessary for the short-term realized variance forecast.