Conference Paper


Exploring efficient model for agricultural commodity price prediction using data analytics

Abstract

The volatility of prices for agricultural commodities exerts a detrimental influence on the gross domestic product of many countries. Price prediction plays a crucial role in aiding the agricultural supply chain in making informed decisions aimed at mitigating and effectively managing the potential risks associated with price changes and supply chain management. While ARIMA and exponential smoothing are commonly employed in forecasting, effectively predicting price movements effectively remains challenges, particularly with extensive datasets. To address this gap, several machine learning and deep learning models have been employed in recent times to predict price series, and this study was accomplished on a publicly available dataset. The primary discovery of this study is that machine learning models demonstrate suitability in predicting commodity prices, having 99% accuracy in predicting a certain level by linear regression.



The fulltext files of this resource are currently embargoed.
Embargo end: 2026-02-27

Authors

Islam, Md Aminul
Nag, Anindya
Basu, Kashinath
Das, Ayontika
Haq, G.M. Mujahidul
Ghosh, Arjan

Oxford Brookes departments

School of Engineering, Computing and Mathematics

Dates

Year of publication: 2025
Date of RADAR deposit: 2025-04-10



“This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the version of record and does not reflect post-acceptance improvements, or any corrections. The version of record is available online."


Related resources

This RADAR resource is the Accepted Manuscript of Exploring Efficient Model for Agricultural Commodity Price Prediction Using Data Analytics

Details

  • Owner: Joseph Ripp
  • Collection: Outputs
  • Version: 1 (show all)
  • Status: Live
  • Views (since Sept 2022): 90