Deep Learning and Econometric Time Series Analysis: An Assessment of Daily Return Forecasts
- We provide an in‐depth assessment of univariate financial time series analysis via machine learning followed by a thorough discussion beyond the discussion on daily return predictability. We simulate economic time series and present an in‐depth assessment of relevant hyperparameter tuning and study the ability of competing deep learning algorithms to capture econometric properties of financial time series. Also, we assess empirical data and discuss competing approaches in comparison with econometric benchmarks, when the data generating process is unknown. As a result, we assess more than 512,000 in‐sample and out‐of‐sample forecasts for different scenarios of competing network architectures. Drawing on realistic sample sizes, we find that recurrent neural networks with one layer describe a solid alternative to econometric autoregressive moving average (ARMA) approach.
| Author: | Theo BergerORCiDGND |
|---|---|
| URN: | urn:nbn:de:bsz:960-opus4-38246 |
| DOI: | https://doi.org/10.25968/opus-3824 |
| DOI original: | https://doi.org/10.1002/for.70045 |
| ISSN: | 0277-6693 |
| ISSN: | 1099-131X |
| Parent Title (English): | Journal of Forecasting |
| Document Type: | Article |
| Language: | English |
| Year of Completion: | 2025 |
| Publishing Institution: | Hochschule Hannover |
| Release Date: | 2026/02/11 |
| Tag: | deep learning; forecasting; machine learning; risk measurement; time series analysis |
| GND Keyword: | Deep LearningGND; Maschinelles LernenGND; RisikomanagementGND; PrognoseverfahrenGND |
| Volume: | 45 |
| Issue: | 1 |
| Page Number: | 14 |
| First Page: | 377 |
| Last Page: | 390 |
| Institutes: | Fakultät IV - Wirtschaft und Informatik |
| DDC classes: | 330 Wirtschaft |
| Licence (German): |  Creative Commons - CC BY - Namensnennung 4.0 International |
