PREDICTING LATE DELIVERIES IN HUMANITARIAN SUPPLY CHAINS: USING AN ENSEMBLE MACHINE LEARNING APPROACH

Fahd Alfarsi; Mohammad Alshehri

Proceedings of ICLT 2024

PREDICTING LATE DELIVERIES IN HUMANITARIAN SUPPLY CHAINS: USING AN ENSEMBLE MACHINE LEARNING APPROACH

Fahd Alfarsi; Mohammad Alshehri

University of Jedda, Saudi Arabia; University of Jedda, Saudi Arabia

International Conference on Logistics & Transport 2024, Seoul, South Korea, pp. 129-134

Download PDF | View interactive page

Abstract

Purpose: This study focuses on predicting late deliveries within humanitarian supply chains using a case study dataset to address this critical issue. Design/ methodology/ approach: This paper proposes several ensemble machine learning methodologies aimed at mitigating shipment risks by predicting the likelihood of late deliveries based on a detailed understanding of the procurement process. Findings:Our findings demonstrate that an ensemble algorithm-based prediction model can effectively forecast the severity of late deliveries by suppliers in a representative case study of humanitarian supply chains. Originality/ value: By providing a better understanding of shipment risks, this study aims to reduce uncertainty and improve the efficiency of humanitarian supply chain operations. This research contributes to the existing literature by showcasing the applicability of advanced machine learning techniques in enhancing the resilience and effectiveness of humanitarian supply chains.

Keywords

Humanitarian Supply Chains; Late Delivery Prediction; Supply Chain Resilience; Machine Learning; Delivery Forecasting

Citation

Fahd Alfarsi; Mohammad Alshehri (2024). PREDICTING LATE DELIVERIES IN HUMANITARIAN SUPPLY CHAINS: USING AN ENSEMBLE MACHINE LEARNING APPROACH. Proceedings of the International Conference on Logistics & Transport (ICLT 2024), Seoul, South Korea, pp. 129-134.