Determinants of the price of bitcoin: An analysis with machine learning and interpretability techniques

José Manuel Carbó and Sergio Gorjón

International Review of Economics & Finance, 2024, vol. 92, issue C, 123-140

Abstract: In this paper we investigate the variables that influence the trading price of bitcoin. Utilizing a Long Short-Term Memory (LSTM) neural network, a flexible machine learning model, we determine bitcoin's price based on various economic, technological, and investor attention factors. The LSTM model replicates bitcoin price behavior reasonably well across different time periods. We then employ the SHAP interpretability approach to identify the most important features affecting the LSTM's outcome. We conclude that, over time, technological variables decrease in importance, while those related to investor attention gain prominence. Moreover, beyond the shifting influence of variables, new explanatory factors seem to appear over time that, at least for the most part, remain initially unknown. Improving the understanding of the factors that influence price formation, as well as its possible (in)stability over time, could help anticipate real risks to the system and, support the design of a regulatory framework that helps contain them.

Keywords: Bitcoin; Machine learning; LSTM; Interpretability techniques (search for similar items in EconPapers)
JEL-codes: C40 C45 G12 G15 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1059056024000704
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:reveco:v:92:y:2024:i:c:p:123-140

DOI: 10.1016/j.iref.2024.01.070

Access Statistics for this article

International Review of Economics & Finance is currently edited by H. Beladi and C. Chen

More articles in International Review of Economics & Finance from Elsevier
Bibliographic data for series maintained by Catherine Liu ().