Bitcoin replication using machine learning

Richard D F Harris*, Murat Mazibas*, Dooruj Rambaccussing*

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

Abstract

Cryptocurrencies are characterized by high volatility and low correlations with traditional asset classes, and present an intriguing investment opportunity. However, their inherent risks and regulatory uncertainties make direct investment challenging for many investors. This paper addresses this challenge by proposing a replication framework that employs machine learning to create synthetic portfolios that replicate the risk-adjusted return profile and diversification benefits of Bitcoin, by far the largest cryptocurrency by market share. We show that the synthetic portfolios offer a compelling alternative to direct investment in Bitcoin, delivering superior risk-adjusted returns net of trading costs while mitigating the risks that are associated with holding Bitcoin directly. Furthermore, the synthetic portfolios provide better diversification benefits and lower tail risk.
Original languageEnglish
Article number103207
Number of pages9
JournalInternational Review of Financial Analysis
Volume93
Early online date12 Mar 2024
DOIs
Publication statusPublished - 1 May 2024

Bibliographical note

Publisher Copyright:
© 2024 The Authors

Fingerprint

Dive into the research topics of 'Bitcoin replication using machine learning'. Together they form a unique fingerprint.

Cite this