Can investors’ informed trading predict cryptocurrency returns? Evidence from machine learning

• Published in: Research in international business and finance Vol. 62; p. 101683
• Main Authors: Wang, Yaqi, Wang, Chunfeng, Sensoy, Ahmet, Yao, Shouyu, Cheng, Feiyang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-12-2022
• Subjects: Behavioral finance; Cryptocurrency; Forecasting; Informed trading; Machine learning; C53; Machine learning; G12; Cryptocurrency; Informed trading; C81; Forecasting; Behavioral finance; D82
• ISSN: 0275-5319; 1878-3384
• DOI: 10.1016/j.ribaf.2022.101683

As an emerging asset, cryptocurrencies have attracted more and more attention from investors and researchers in recent years. With the gradual convergence of the investors in cryptocurrency and traditional financial markets, the research on investor trading behavior from the perspective of microstructure has become increasingly important in cryptocurrency market. In this paper, we study whether investors’ informed trading behavior can significantly predict cryptocurrency returns. We use various machine learning algorithms to verify the contribution of informed trading to the predictability of cryptocurrency returns. The results show that informed trading plays a role in the prediction of some individual cryptocurrency returns, but it cannot significantly improve the prediction accuracy in an average sense of the whole market. The lack of market supervision of cryptocurrency market may be the main factor for relatively low efficiency of this market, and policymakers need to pay attention to it.
[Display omitted]
•This paper examines whether informed trading can predict cryptocurrency returns.•We use some machine learning algorithms to verify its predictability.•Informed trading can predict individual cryptocurrency returns to a certain extent.•Indicators of informed trading do not make a significant effect on an average sense.•Other investor behavior indicators also have no contribution on prediction accuracy.