Inferring short-term volatility indicators from Bitcoin blockchain

TL;DR

This paper explores how features derived from Bitcoin transaction graphs can be used to predict short-term extreme price volatility, providing a novel approach to early warning indicators based on blockchain data.

Contribution

It introduces a new method for inferring early warning indicators from Bitcoin transaction graphs that outperform traditional scalar volume measures.

Findings

Graph-based features improve volatility prediction accuracy

Non-negative decomposition yields more predictive indicators

Blockchain transaction data can serve as early warning signals

Abstract

In this paper, we study the possibility of inferring early warning indicators (EWIs) for periods of extreme bitcoin price volatility using features obtained from Bitcoin daily transaction graphs. We infer the low-dimensional representations of transaction graphs in the time period from 2012 to 2017 using Bitcoin blockchain, and demonstrate how these representations can be used to predict extreme price volatility events. Our EWI, which is obtained with a non-negative decomposition, contains more predictive information than those obtained with singular value decomposition or scalar value of the total Bitcoin transaction volume.