Taming Data‐Driven Probability Distributions
Open Access
- 19 November 2024
- journal article
- research article
- Published by Wiley in Journal of Forecasting
- Vol. 44 (2) , 676-691
Abstract
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.Keywords
Funding Information
- Grantová Agentura České Republiky (EXPRO GX19‐28231X)
This publication has 42 references indexed in Scilit:
- How is machine learning useful for macroeconomic forecasting?Journal of Applied Econometrics, 2022
- Distributional modeling and forecasting of natural gas pricesJournal of Forecasting, 2022
- Does it pay to follow anomalies research? Machine learning approach with international evidenceJournal of Financial Markets, 2021
- Criteria for classifying forecasting methodsInternational Journal of Forecasting, 2020
- On the directional predictability of equity premium using machine learning techniquesJournal of Forecasting, 2019
- Forecasting dynamic return distributions based on ordered binary choiceInternational Journal of Forecasting, 2019
- Deep learning for finance: deep portfoliosApplied Stochastic Models in Business and Industry, 2016
- Bayesian forecasting in economicsInternational Journal of Forecasting, 2010
- Forecasting with Exponential Smoothing2008
- Density forecasting in economics and financeJournal of Forecasting, 2000