Machine learning platinum price predictions

Bingzi Jin and Xiaojie Xu

The Engineering Economist, 2025, vol. 70, issue 1-2, 30-56

Abstract: Throughout history, governments and investors have placed trust in price predictions for a wide range of commodities. This research explores the complex problem of forecasting daily platinum prices for the United States using time-series data spanning from January 02, 1969 to March 15, 2024. Estimates have not received enough attention in previous studies for this important assessment of commodity pricing. Here, price projections are created by using Gaussian process regression algorithms that are estimated with the use of cross-validation procedures and Bayesian optimization techniques. Arriving at the relative root mean square error of 1.5486%, our empirical prediction method yields relatively precise price projections for the out-of-sample phase covering 04/03/2013–03/15/2024. Price prediction models can be used by governments and investors to make informed decisions regarding the platinum business.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/0013791X.2025.2464130 (text/html)
Access to full text is restricted to subscribers.

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:taf:uteexx:v:70:y:2025:i:1-2:p:30-56

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/UTEE20

DOI: 10.1080/0013791X.2025.2464130

Access Statistics for this article

The Engineering Economist is currently edited by Sarah Ryan

More articles in The Engineering Economist from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().