SCAIL · Supply Chain AI Lab Data Hub

Delay Prediction

Yunbo Long 464 words 3 minutes Machine Learning Forecasting Logistics

Delay prediction is a critical capability in modern supply chain management, where even small disruptions in delivery timelines can cascade into significant operational and financial consequences. As global supply chains grow more complex and interconnected, the ability to anticipate delays—before they occur—has become a key differentiator for resilient organisations.

Traditional approaches to managing delivery delays relied heavily on historical averages and rule-based heuristics. However, advances in machine learning and data-driven analytics have opened new avenues for predictive modelling. Techniques ranging from gradient boosting and random forests to deep learning and graph neural networks are now being applied to forecast delays at various stages of the supply chain—from supplier lead times and manufacturing throughput to last-mile logistics.

A growing body of research, including work from the Supply Chain AI Lab at the University of Cambridge, has demonstrated the value of combining structured supply chain data (e.g., purchase orders, shipment records) with external signals (e.g., weather, port congestion, geopolitical events) to improve prediction accuracy. These methods not only enhance operational planning but also support proactive risk mitigation strategies.

We invite you to explore the curated collection of key publications below, offering insights into the evolution and state of the art in supply chain delay prediction.

List of Publications

  1. Brintrup, A., Pak, J., Ratiney, D., Pearce, T., Wichmann, P., Woodall, P. and McFarlane, D., 2020. Supply chain data analytics for predicting supplier disruptions: A case study in complex asset manufacturing. International Journal of Production Research, 58(11), pp.3330-3341. [PDF]
  2. Xu, L., Brintrup, A. and Chattopadhyay, I., 2024. Delay prediction in supply chains using graph neural networks. IFAC-PapersOnLine, 58(19), pp.801-806. [PDF]
  3. Kosasih, E.E. and Brintrup, A., 2022. A machine learning approach for predicting hidden links in supply chain with graph neural networks. International Journal of Production Research, 60(17), pp.5380-5393. [PDF]
  4. Brintrup, A., Wichmann, P., Woodall, P., McFarlane, D., Nicks, E. and Krechel, W., 2018. Predicting hidden links in supply networks. Complexity, 2018, 9104387. [PDF]
  5. Wichmann, P., Brintrup, A., Baker, S., Woodall, P. and McFarlane, D., 2020. Extracting supply chain maps from news articles using deep neural networks. International Journal of Production Research, 58(17), pp.5320-5336. [PDF]
  6. Kosasih, E.E., Margaroli, F., Gelli, S., Aziz, A., Wildgoose, N. and Brintrup, A., 2024. Towards knowledge graph reasoning for supply chain risk management using graph neural networks. International Journal of Production Research, 62(15), pp.5596-5612. [PDF]