Graph Neural Networks for Supply Chain Management: A Framework and Real World Benchmark
Authors: Azmine Toushik Wasi, MD Shafikul Islam
Organizations: Department of Industrial and Production Engineering, Shahjalal University of Science and Technology, Sylhet, Bangladesh · Department of Mechanincal and Industrial Engineering, Louisiana State University, Baton Rounge, LA, 70803, USA
Graph Neural Networks (GNNs) have recently gained traction in transportation, bioinformatics, language and image processing, but research on their application to supply chain management remains limited. Supply chains are inherently graph-like, making them ideal for GNN methodologies, which can optimize and solve complex problems. The barriers include a lack of proper conceptual foundations, familiarity with graph applications in SCM, and real-world benchmark datasets for GNN-based supply chain research. To address this, we discuss and connect supply chains with graph structures for effective GNN application, providing detailed formulations, examples, mathematical definitions, and task guidelines. Additionally, we present a multi-perspective real-world benchmark dataset from a leading FMCG company in Bangladesh, focusing on supply chain planning. We discuss various supply chain tasks using GNNs and benchmark several state-of-the-art models on homogeneous and heterogeneous graphs across six supply chain analytics tasks. Our analysis shows that GNN-based models consistently outperform statistical Machine Learning and other Deep Learning models by around 10-30% in regression, 10-30% in classification and detection tasks, and 15-40% in anomaly detection tasks on designated metrics. With this work, we lay the groundwork for solving supply chain problems using GNNs, supported by conceptual discussions, methodological insights, and a comprehensive dataset.
Figures & tables
Figure 1: Supply Chain as a Graph of Interconnected Company, Products, Distributors and Customers.
Figure 2: Supply Chain Problem Formulation in Homogeneous Graph. Boxes represent various product types, with colour indicating different groups. They are closely located based on product groups and production facilities. Different relational connections denote shared raw material requirements, interdependence between products, and other impacts.
Figure 3: Heterogeneous Graph Example using SCG dataset. Products, plants, and storage locations are nodes and their relations are edges.
Figure 4: Homogeneous Graph Examples using SCG dataset.
College of Engineering, Northeastern University Boston, USA · School of Engineering, Santa Clara University Santa Clara, USA · Department of Chemistry and Chemical Biology, University of New Mexico Albuquerque, USA