Fear and Volatility in Digital Assets

TL;DR

This paper demonstrates that Bitcoin's implied volatility can be predicted over short time horizons using a combination of price data, volatility momentum, sentiment, and engagement metrics, with market responses lagging behind these signals.

Contribution

It introduces a predictive model for Bitcoin implied volatility that incorporates alternative data sources like sentiment and engagement, showing their significance in short-term volatility forecasting.

Findings

Bitcoin implied volatility is modestly predictable from various data sources.

Lagged market movements and Google Trends influence volatility predictions.

The study provides open-source code and datasets for further research.

Abstract

We show Bitcoin implied volatility on a 5 minute time horizon is modestly predictable from price, volatility momentum and alternative data including sentiment and engagement. Lagged Bitcoin index price and volatility movements contribute to the model alongside Google Trends with markets responding often several hours later. The code and datasets used in this paper can be found at https://github.com/Globe-Research/bitfear.