Deep Fusion of Lead-lag Graphs: Application to Cryptocurrencies

TL;DR

This paper introduces a novel deep learning method for representing lead-lag relationships in cryptocurrency time series, capturing both synchronous and asynchronous dependencies to improve understanding of asset co-movements.

Contribution

The paper presents a new deep fusion algorithm for lead-lag graphs that effectively integrates synchronous and asynchronous relationships in multivariate time series.

Findings

Enhanced detection of hidden asset dependencies

Improved modeling of asynchronous relationships

Better understanding of cryptocurrency co-movements

Abstract

The study of time series has motivated many researchers, particularly on the area of multivariate-analysis. The study of co-movements and dependency between random variables leads us to develop metrics to describe existing connection between assets. The most commonly used are correlation and causality. Despite the growing literature, some connections remained still undetected. The objective of this paper is to propose a new representation learning algorithm capable to integrate synchronous and asynchronous relationships.