On multi-horizon forecasting of copper price returns using deep learning techniques

M. Carhuas, Soledad Espezua, Edwin Villanueva

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Forecasting copper prices is vital for stakeholders in industries reliant on this commodity. The challenge arises from the market's dynamism and the multitude of factors affecting prices. This study introduces neural network models for predicting short-term copper price returns. Utilizing historical pricing data and macroeconomic indicators from 2007 to 2021, we discover that models dedicated to specific forecasting horizons outshine those designed for multiple horizons. Notably, Long Short- Term Memory (LSTM) models consistently delivered the most accurate predictions for both one-week and one-month future returns, confirming their robustness in capturing the complex patterns inherent in the copper market.

Original languageEnglish
Title of host publicationIEEE Andescon, ANDESCON 2024 - Proceedings
Place of PublicationLima
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350355284
DOIs
StatePublished - 2024
Event12th IEEE Andescon, ANDESCON 2024 - Cusco, Peru
Duration: 11 Sep 202413 Sep 2024

Conference

Conference12th IEEE Andescon, ANDESCON 2024
Country/TerritoryPeru
CityCusco
Period11/09/2413/09/24

Bibliographical note

Publisher Copyright:
© 2024 IEEE.

Keywords

  • Copper Price Forecasting
  • Deep Learning
  • Multi-step Forecasting
  • Recurrent Neural Networks
  • Time Series

Fingerprint

Dive into the research topics of 'On multi-horizon forecasting of copper price returns using deep learning techniques'. Together they form a unique fingerprint.

Cite this