Year: 2024
Type: article
Abstract: ABSTRACT In this study, we aim to identify the machine learning model that can overcome the limitations of traditional statistical modelling techniques in forecasting Bitcoin prices. Also, we outline the necessary conditions that make the model suitable. We draw on a multivariate large data set of Bitcoin prices and its market microstructure variables and apply three machine learning models, namely double deep Q‐learning, XGBoost and ARFIMA‐GARCH. The findings show that the double deep Q‐learning model outperforms the others in terms of returns and Sortino ratio and is capable of one‐step‐ahead sign forecast of the returns even on synthetic data. These critical insights in forecasting literature will support practitioners and regulators to identify an economically viable cryptocurrency forecasting return model.
DOI: 10.1002/ijfe.3062
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: hybrid
Estimated APC paid: $3,240
OpenAlex ID: W4404488538