EUVIMEDOpdag EUVIMED
Open access · CC BY-NC-ND 4.0

Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning

Theo Berger, Jana Koubová

Journal of Forecasting · 2024-11 · 43 (7) · 2904-2916

DOI: 10.1002/for.3165 ↗

At a glance

Journal article in Journal of Forecasting, published online on 2024-05-31. Written by Theo Berger and 1 co-authors. Cited 19 times so far (Crossref); 35 references. The full text is freely available (open access, CC BY-NC-ND 4.0).

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

We study the statistical properties of the Bitcoin return series and provide a thorough forecasting exercise. Also, we calibrate state‐of‐the‐art machine learning techniques and compare the results with econometric time series models. The empirical assessment provides evidence that the application of machine learning techniques outperforms econometric benchmarks in terms of forecasting precision for both in‐ and out‐of‐sample forecasts. We find that both deep learning architectures as well as complex layers, such as LSTM, do not increase the precision of daily forecasts. Specifically, a simple recurrent neural network describes a sensible choice for forecasting daily return series.

Cite

APA

Berger, T., & Koubová, J. (2024). Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning. Journal of Forecasting, 43(7), 2904-2916. https://doi.org/10.1002/for.3165

Vancouver

Berger T, Koubová J. Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning. Journal of Forecasting. 2024;43(7):2904-2916. doi:10.1002/for.3165

BibTeX
@article{Berger2024,
  author = {Berger, Theo and Koubová, Jana},
  title = {Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning},
  journal = {Journal of Forecasting},
  year = {2024},
  volume = {43},
  number = {7},
  pages = {2904--2916},
  doi = {10.1002/for.3165}
}
Start for free →