Bitcoin Volatility Forecasting with a Glimpse into Buy and Sell Orders

TL;DR

This paper explores short-term Bitcoin price volatility prediction using realized volatility data and order information, evaluating various statistical and machine learning models on real trading data from 2016-2017.

Contribution

It introduces a comprehensive analysis of Bitcoin volatility forecasting incorporating order data and compares multiple predictive models.

Findings

Certain models outperform others in short-term volatility prediction

Order information improves forecasting accuracy

Statistical and machine learning approaches have varying effectiveness

Abstract

In this paper, we study the ability to make the short-term prediction of the exchange price fluctuations towards the United States dollar for the Bitcoin market. We use the data of realized volatility collected from one of the largest Bitcoin digital trading offices in 2016 and 2017 as well as order information. Experiments are performed to evaluate a variety of statistical and machine learning approaches.