Forecasting Bitcoin returns: Econometric time series analysis vs. machine learning
- 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.
| Author: | Theo BergerORCiDGND, Jana Koubová |
|---|---|
| URN: | urn:nbn:de:bsz:960-opus4-31780 |
| DOI: | https://doi.org/10.25968/opus-3178 |
| DOI original: | https://doi.org/10.1002/for.3165 |
| ISSN: | 1099-131X |
| Parent Title (English): | Journal of Forecasting |
| Publisher: | Wiley |
| Document Type: | Article |
| Language: | English |
| Year of Completion: | 2024 |
| Publishing Institution: | Hochschule Hannover |
| Release Date: | 2024/10/15 |
| Tag: | forecasting; machine learning; risk measurement; time series analysis |
| GND Keyword: | Prognose; Maschinelles Lernen; Risikoanalyse; Zeitreihenanalyse; Bitcoin |
| Volume: | 43 |
| Issue: | 7 |
| First Page: | 2904 |
| Last Page: | 2916 |
| Link to catalogue: | 1910694797 |
| Institutes: | Fakultät IV - Wirtschaft und Informatik |
| DDC classes: | 330 Wirtschaft |
| Licence (German): |  Creative Commons - CC BY-NC-ND - Namensnennung - Nicht kommerziell - Keine Bearbeitungen 4.0 International |
