EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Taming Data‐Driven Probability Distributions

Jozef Baruník, Luboš Hanus

Journal of Forecasting · 2025-03 · 44 (2) · 676-691

DOI: 10.1002/for.3208 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Forecasting, online erschienen am 19.11.2024. Verfasst von Jozef Baruník und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Grantová Agentura České Republiky.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We propose a deep learning approach to probabilistic forecasting of macroeconomic and financial time series. By allowing complex time series patterns to be learned from a data‐rich environment, our approach is useful for decision making that depends on the uncertainty of a large number of economic outcomes. In particular, it is informative for agents facing asymmetric dependence of their loss on the outcomes of possibly non‐Gaussian and nonlinear variables. We demonstrate the usefulness of the proposed approach on two different datasets where a machine learns patterns from the data. First, we illustrate the gains in predicting stock return distributions that are heavy tailed and asymmetric. Second, we construct macroeconomic fan charts that reflect information from a high‐dimensional dataset.

Förderung

  • Grantová Agentura České Republiky

Zitieren

APA

Baruník, J., & Hanus, L. (2025). Taming Data‐Driven Probability Distributions. Journal of Forecasting, 44(2), 676-691. https://doi.org/10.1002/for.3208

Vancouver

Baruník J, Hanus L. Taming Data‐Driven Probability Distributions. Journal of Forecasting. 2025;44(2):676-691. doi:10.1002/for.3208

BibTeX
@article{Barunk2025,
  author = {Baruník, Jozef and Hanus, Luboš},
  title = {Taming Data‐Driven Probability Distributions},
  journal = {Journal of Forecasting},
  year = {2025},
  volume = {44},
  number = {2},
  pages = {676--691},
  doi = {10.1002/for.3208}
}
Kostenlos starten →