Forecasting the term structure of commodities future prices using machine learning

Mario Figueiredo () and Yuri F. Saporito ()
Additional contact information
Mario Figueiredo: Instituto de Matemática Pura e Aplicada
Yuri F. Saporito: Getulio Vargas Foundation

Digital Finance, 2023, vol. 5, issue 1, No 4, 57-90

Abstract: Abstract We consider the dynamic Nelson–Siegel and the Schwartz–Smith three-factor models for future price curves. We study the prediction of the 1-day ahead prices of the entire curve for each model, using two different approaches: ordinary least squares (OLS) and filtering. For the dynamic Nelson–Siegel, we test the random walk, VAR and models based on long short-term memory (LSTM), including a filtering approach using LSTM. For the Schwartz–Smith model, we use the equations given by no-arbitrage assumptions. We also test a model that tries to predict the prices directly from the curve, which we refer to as basic model. We exemplify our approach using Brent, WTI and Copper future prices. We show that the dynamic Nelson–Siegel was the best model for fitting the data, and that the LSTM and VAR methods under the OLS approach generated the best forecasts.

Keywords: Future prices; Forecasting; Deep learning; Commodities; Dynamic Nelson–Siegel; Schwartz–Smith model (search for similar items in EconPapers)
JEL-codes: C14 G13 G17 (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s42521-022-00069-3 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

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:spr:digfin:v:5:y:2023:i:1:d:10.1007_s42521-022-00069-3

Ordering information: This journal article can be ordered from
https://www.springer.com/finance/journal/42521

DOI: 10.1007/s42521-022-00069-3

Access Statistics for this article

Digital Finance is currently edited by Wolfgang Karl Härdle, Steven Kou and Min Dai

More articles in Digital Finance from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().