Efficient market hypothesis on the blockchain: A social‐media‐based index for cryptocurrency efficiency

Polyzos, Efstathios; Rubbaniy, Ghulame; Mazur, Mieszko

Abstract

This paper proposes the use of social media as a proxy for financial information. Using an extended sample of 53,580,759 tweets and employing text analysis tools (Latent Dirichlet Allocation and Term Frequency–Inverse Document Frequency), we determine the information being exchanged on any given day. We train machine-learning classifiers and forecast crypto price movements for more than 8000 cryptocurrencies and gauge market efficiency through successful forecasts based on public information. We propose various metrics of market efficiency for cryptocurrency assets and demonstrate that market efficiency is higher during the first 6 months after the Initial Coin Offering. We also examine the efficiency behavior of individual currencies during crisis periods.

• Journal Article Type: Article
• Acceptance Date: Mar 13, 2024
• Online Publication Date: Mar 23, 2024
• Publication Date: Aug 31, 2024
• Deposit Date: Nov 12, 2024
• Publicly Available Date: Mar 24, 2026
• Journal: Financial Review
• Print ISSN: 0732-8516
• Electronic ISSN: 1540-6288
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Volume: 59
• Issue: 3
• Pages: 807-829
• DOI: https://doi.org/10.1111/fire.12387
• Keywords: Economics and Econometrics; Finance
• Public URL: https://uwe-repository.worktribe.com/output/11867644
• Additional Information: Published: 2024-03-23