Article: An integrated approach based on classification and forecasting intermittent demand model for urban pick-up: a case study of Moroccan carrier Journal: International Journal of Logistics Systems and Management (IJLSM) 2025 Vol.51 No.1 pp.1 - 41 Abstract: Pick-up links play a crucial role in logistics chains. It is the most expensive and polluting part of urban logistics. Management and decision-making must be optimised to improve their performance, and develop urban logistics sustainably. Several factors make its management difficult. Due to that, this process produces intermittent demand series. Our aim in this paper is to improve the pick-up chain by anticipating customers' requests. Based on K-means clustering, the integrated approach proposes two novel estimation models for demand occurrence, followed by a forecasting model derived from benchmarking studies between three methods: SES, Croston, and SBA on a real dataset. Our approach demonstrates the value of the classification model and the outperformance of SBA over other methods. This area has not been researched. Thus, this study contributes to urban logistics durability and freight transportation. Consequently, carriers will be provided with new-and-improved benefits in the future based on this relevant context. Inderscience Publishers - linking academia, business and industry through research

Title: An integrated approach based on classification and forecasting intermittent demand model for urban pick-up: a case study of Moroccan carrier

Authors: Leila Bourrich; Saâd Lissane Elhaq

Addresses: Laboratory of Research in Engineering, LRI, Optimization of Production Systems and Energy Team, Higher National School of Electricity and Mechanics, Hassan II University of Casablanca, Casablanca, Morocco ' Laboratory of Research in Engineering, LRI, Optimization of Production Systems and Energy Team, Higher National School of Electricity and Mechanics, Hassan II University of Casablanca, Casablanca, Morocco

Abstract: Pick-up links play a crucial role in logistics chains. It is the most expensive and polluting part of urban logistics. Management and decision-making must be optimised to improve their performance, and develop urban logistics sustainably. Several factors make its management difficult. Due to that, this process produces intermittent demand series. Our aim in this paper is to improve the pick-up chain by anticipating customers' requests. Based on K-means clustering, the integrated approach proposes two novel estimation models for demand occurrence, followed by a forecasting model derived from benchmarking studies between three methods: SES, Croston, and SBA on a real dataset. Our approach demonstrates the value of the classification model and the outperformance of SBA over other methods. This area has not been researched. Thus, this study contributes to urban logistics durability and freight transportation. Consequently, carriers will be provided with new-and-improved benefits in the future based on this relevant context.

Keywords: forecasting methods; intermittent demand; K-means clustering; pick-ups' demand-anticipation; freight transportation.

DOI: 10.1504/IJLSM.2025.146062

International Journal of Logistics Systems and Management, 2025 Vol.51 No.1, pp.1 - 41

Received: 24 Sep 2022
Accepted: 16 Oct 2022
Published online: 06 May 2025 *

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

Title: An integrated approach based on classification and forecasting intermittent demand model for urban pick-up: a case study of Moroccan carrier

Keep up-to-date