Wavelet and Deep Learning Framework for Predicting Commodity Prices Under Economic and Financial Uncertainty

Lyubov Doroshenko (), Loretta Mastroeni and Alessandro Mazzoccoli
Additional contact information
Lyubov Doroshenko: Department of Economics, Roma Tre University, Via Silvio D’Amico 77, 00145 Rome, Italy
Loretta Mastroeni: Department of Economics, Roma Tre University, Via Silvio D’Amico 77, 00145 Rome, Italy
Alessandro Mazzoccoli: Department of Economics, Roma Tre University, Via Silvio D’Amico 77, 00145 Rome, Italy

Mathematics, 2025, vol. 13, issue 8, 1-19

Abstract: The analysis of commodity markets—particularly in the energy and metals sectors—is essential for understanding economic dynamics and guiding decision-making. Financial and economic uncertainty indices provide valuable insights that help reduce price uncertainty. This study employs wavelet analyses and wavelet energy-based measures to investigate the relationship between these indices and commodity prices across multiple time scales. The wavelet approach captures complex, time-varying dependencies, offering a more nuanced understanding of how uncertainty indices influence commodity price fluctuations. By integrating this analysis with predictability measures, we assess how uncertainty indices enhance forecasting accuracy. We further incorporate deep learning models capable of capturing sequential patterns in financial time series into our analysis to better evaluate their predictive potential. Our findings highlight the varying impact of financial and economic uncertainty on the predictability of commodity prices, showing that while some indices offer valuable forecasting information, others display strong correlations without significant predictive power. These results underscore the need for tailored predictive models, as different commodities react differently to the same financial conditions. By combining wavelet-based measures with machine learning techniques, this study presents a comprehensive framework for evaluating the role of uncertainty in commodity markets. The insights gained can support investors, policymakers, and market analysts in making more informed decisions.

Keywords: wavelet analysis; predictability; energy-based measure; commodities; deep learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/8/1346/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/8/1346/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:8:p:1346-:d:1638516

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().