Title: Forecasting agricultural product logistics demand by nonlinear principal component analysis and a support vector machine optimised by the grey wolf optimiser

Authors: Xiaoye Zhou; Meilin Zhu; Xiaoyun Ma; Yu Zhong

Addresses: School of Management, Shenyang University of Technology, Shenyang, 110870, China ' School of Management, Shenyang University of Technology, Shenyang, 110870, China ' School of Management, Shenyang University of Technology, Shenyang, 110870, China ' School of Management, Shenyang University of Technology, Shenyang, 110870, China

Abstract: Artificial intelligence systems can use machine learning algorithms to remarkably improve logistics demand forecasting. This study proposes a novel agri-product logistics demand forecasting model based on a hybrid approach of nonlinear principal component analysis and a grey wolf optimiser-based support vector regression machine. Its performance is investigated experimentally using a case study of agri-product logistics demand in Liaoning Province, China. Comparison with similar models demonstrates that: 1) the proposed model more accurately forecasts agri-product logistics demand; 2) nonlinear principal component analysis significantly outperforms conventional principal component analysis; 3) the grey wolf optimiser greatly improves the performance of the support vector regression machine.

Keywords: forecasting model; support vector regression machine; SVR; nonlinear principal component analysis; NLPCA; grey wolf optimiser; GWO; agri-product logistics demand.

DOI: 10.1504/IJIMS.2021.122717

International Journal of Internet Manufacturing and Services, 2021 Vol.8 No.2, pp.150 - 171

Received: 28 Oct 2021
Accepted: 14 Feb 2022
Published online: 06 May 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article