AI-Driven Cascading Risk Prediction in Multi-Tier Supply Chain Networks Using Graph Neural Networks

References

[1] P. Wichmann, A. Brintrup, S. Baker, P. Woodall, and D. McFarlane, “Extracting supply chain maps from news articles using deep neural networks,” International Journal of Production Research , vol. 58, no. 17, pp. 5320–5336, Feb. 2020,

[2] J. Liu, P. Li, and Y. Wang, “Graph Neural Networks for Modeling Complex Dependencies in Global Supply Chain Networks,” Journal of Computing and Electronic Information Management , vol. 20, no. 3, pp. 9–20, Mar. 2026,

[3] F. N. Nitu, M. M. Mia, M. Roy, S. Yezdani, B. FINDIK, and R. A. Nipa, “Leveraging Graph Neural Networks for Intelligent Supply Chain Risk Management in the Era of Industry 4.0,” International Interdisciplinary Business Economics Advancement Journal , vol. 6, no. 10, pp. 21– 33, Oct. 2025, 03 .

[4] S. Petrova and M. Hughes1, “Physics-Informed Graph Neural Networks for Supply Chain Disruption Prediction and Mitigation,” Frontiers in Applied Physics and Mathematics , vol. 2, no. 1, pp. 130–147, Dec. 2025, 10.71465/fapm458 .

[5] A. Aziz, E. E. Kosasih, R. Griffiths, and A. Brintrup, “Data Considerations in Graph Representation Learning for Supply Chain Networks,” Jul. 22, 2021, Cornell University .

[6] D. Ivanov, “Simulation-based ripple effect modelling in the supply chain,” International Journal of Production Research , vol. 55, no. 7, pp. 2083–2101, Jan. 2017, 10.1080/00207543.2016.1275873 .

[7] T. Zhang, J. Li, and F. Bénaben, “A Simulation Framework Dedicated to Characterizing Risks and Cascading Effects in Collaborative Networks,” in IFIP advances in information and communication technology , Springer Science+Business Media, 2022, pp. 463–474. 10.1007/978-3-031-14844-6_37 .

[8] A. Dolgui, D. Ivanov, and B. Sokolov, “Ripple effect in the supply chain: an analysis and recent literature,” International Journal of Production Research , vol. 56, pp. 414–430, Oct. 2017, 10.1080/00207543.2017.1387680 .

[9] E. E. Kosasih and A. Brintrup, “A machine learning approach for predicting hidden links in supply chain with graph neural networks,” International Journal of Production Research , vol. 60, no. 17, pp. 5380–5393, Jul. 2021,

[10] A. Llaguno, J. Mula, and F. C. Bolarín, “State of the art, conceptual framework and simulation analysis of the ripple effect on supply chains,” International Journal of Production Research , vol. 60, no. 6, pp. 2044–2066, Feb. 2021,

[11] L. Wang, F. Yao, Z. Wu, and R. Gao, “Simulation system design for critical-node detection and robustness analysis of supply chains,” Enterprise Information Systems , vol. 18, no. 5, Mar. 2024,

[12] A. Kinra, D. Ivanov, A. Das, and A. Dolgui, “Ripple effect quantification by supplier risk exposure assessment,” International Journal of Production Research , vol. 58, no. 18, pp. 5559 –5578, Oct. 2019, 10.1080/00207543.2019.1675919 .

[13] O. A. Ajayi, “Anticipating supply chain disruptions with graph AI models,” World Journal of Advanced Engineering Technology and Sciences , vol. 7, no. 1, pp. 241–244, Oct. 2022,

[14] N. Brockmann, E. E. Kosasih, and A. Brintrup, “Supply Chain Link Prediction on Uncertain Knowledge Graph,” ACM SIGKDD Explorations Newsletter , vol. 24, no. 2, pp. 124–130, Nov. 2022,

[15] E. E. Kosasih, F. Margaroli, S. Gelli, A. Aziz, N. Wildgoose, and A. Brintrup, “Towards knowledge graph reasoning for supply chain risk management using graph neural networks,” International Journal of Production Research , vol. 62, no. 15, pp. 5596–5612, Jul. 2022, 10.1080/00207543.2022.2100841 .

[16] Z. Ge and A. Brintrup, “Enhancing Supply Chain Visibility with Generative AI: An Exploratory Case Study on Relationship Prediction in Knowledge Graphs,” Dec. 04, 2024, Cornell University . 10.48550/arxiv.2412.03390 .

[17] G. Baryannis, S. Dani, and G. Antoniou, “Predicting supply chain risks using machine learning: The trade-off between performance and interpretability,” Future Generation Computer Systems , vol. 101, pp. 993–1004, Jul. 2019, 10.1016/j.future.2019.07.059 .

[18] N. Rezki and M. Mansouri, “Integrating machine learning and deep learning for enhanced supplier risk prediction,” Acta Logistica , vol. 11, no. 3, pp. 387–396, Sep. 2024, 10.22306/al.v11i3.523 .

[19] Z. Ge, L. Kong, and A. Brintrup, “Federated machine learning for privacy preserving, collective supply chain risk prediction,” International Journal of Production Research , vol. 61, no. 23, pp. 8115–8132, Feb. 2023, 10.1080/00207543.2022.2164628 .

[20] N. Kotecha and E. A. del Rio‐Chanona, “Leveraging graph neural networks and multi-agent reinforcement learning for inventory control in supply chains,” Computers & Chemical Engineering , vol. 199, p. 109111, Apr. 2025, 10.1016/j.compchemeng.2025.109111 .

[21] F. Stranieri, F. Stella, and C. Kouki, “Performance of deep reinforcement learning algorithms in two-echelon inventory control systems,” International Journal of Production Research , vol. 62, no. 17, pp. 6211–6226, Mar. 2024,

[22] K. Geevers, L. van Hezewijk, and M. Mes, “Multi-echelon inventory optimization using deep reinforcement learning,” Central European Journal of Operations Research , vol. 32, no. 3, pp. 653–683, Jul. 2023, 00872-2 .

[23] D. Ivanov and A. Dolgui, “Stress testing supply chains and creating viable ecosystems,” Operations Management Research , vol. 15, pp. 475–486, May 2021, 10.1007/s12063-021-00194-z .

[24] Md. I. Hossain, S. Talapatra, P. Saha, and H. M. Belal, “From Theory to Practice: Leveraging Digital Twin Technologies and Supply Chain Disruption Mitigation Strategies for Enhanced Supply Chain Resilience with Strategic Fit in Focus,” Global Journal of Flexible Systems Management , vol. 26, no. 1, pp. 87–109, Dec. 2024, 10.1007/s40171-024-00424-w .

[25] N. K. Jingar, “Ensuring Safety, Accountability, and Drift Resistance in LLM-Based Supply Chain Optimization,” International Journal of Scientific Research in Science Engineering and Technology , p. 472, Jan. 2023, 10.32628/ijsrset2310372 .

[26] Z. Shen, H. Wang, J. Chen, and X. Song, “Resilience Inference for Supply Chains with Hypergraph Neural Network,” in Proceedings of the AAAI Conference on Artificial Intelligence , Association for the Advancement of Artificial Intelligence, Mar. 2026, pp. 39259–39267. 10.1609/aaai.v40i46.41274 .

[27] M. R. I. Khan, “AI-powered predictive analytics for enhancing supply chain resilience and delivery outcomes,” Discover Analytics , vol. 4, no. 1, Apr. 2026, 10.1007/s44257-026-00065-6 .

[28] J. Wang, “Multimodal Deep Learning Approach for Early Warning of Supply Chain Disruptions Using NLP and Anomaly Detection,” Artificial Intelligence and Machine Learning Review , vol. 5, no. 3, pp. 98–110, Jul. 2024, 10.69987/aimlr.2024.50308 .

[29] K. Kasali, A. O. Olawore, and A. Raji, “Machine learning applications in early warning systems for supply chain disruptions: strategies for adapting to risk, pandemics and enhancing business resilience and economic stability,” International Journal of Science and Research Archive , vol. 15, no. 2, pp. 1829–1845, May 2025, 10.30574/ijsra.2025.15.2.1612 .

[30] S. A. H. Zaidi, S. A. Khan, and A. Chaabane, “Unlocking the potential of digital twins in supply chains: A systematic review,” Supply Chain Analytics , vol. 7, p. 100075, Jul. 2024,

[31] N. K. Jingar, “Automated Incident Intelligence In Supply Chains Using Agentic AI And Root Cause Reasoning,” Zenodo (CERN European Organization for Nuclear Research) , Sep. 2023,

[32] Sichong Huang, “AI-Driven Early Warning Systems for Supply Chain Risk Detection: A Machine Learning Approach,” Academic Journal of Computing & Information Science , vol. 8, no. 9, Jan. 2025, 10.25236/ajcis.2025.080913 .

[33] W. J. Tan, W. Cai, and A. N. Zhang, “Structural-aware simulation analysis of supply chain resilience,” International Journal of Production Research , vol. 58, no. 17, pp. 5175 –5195, Dec. 2019, 10.1080/00207543.2019.1705421 .

@article{1725050,
      author = {Sohail Sayed, Nauman Sayed, Muhammad Khurram Khan},
      title = {AI-Driven Cascading Risk Prediction in Multi-Tier Supply Chain Networks Using Graph Neural Networks},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {7},
      pages = {3056-3063},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1725050.pdf},
      abstract = {Multi-tier supply chains are complex, emergent networks in which a single upstream disruption can cascade across tiers, and visibility beyond tier-1 suppliers is the exception rather than the rule: complex products are assembled from tens of thousands or even millions of parts sourced through increasingly opaque sub-tier networks [1]. This paper addresses systemic supply-chain risk — the risk that propagates through network structure itself — using graph neural networks, the model family explicitly designed to capture non-local, multi-entity dependencies that classical analytics miss [2]. We propose a cascade-aware GNN framework with three coupled prediction tasks: (i) node-level cascade-impact classification at a forecast horizon, (ii) link prediction over the multi-tier dependency graph to expose hidden supplier relationships, and (iii) aggregate ripple-amplification and recovery-time estimation. The framework couples a tier-aware temporal message-passing encoder, a knowledge-graph reasoning module, and Integrated-Gradient explainability, and it is positioned as the graph-native core between the multi-signal early warning layer and the agentic decision layer of our prior work. Reported evidence consolidates the performance envelope: graph attention networks reach 92.1% accuracy with an AUC of 0.97 for high-risk supplier identification [3]; physics-informed GNNs reduce disruption prediction error by 23% relative to purely data-driven GNNs [4]; and GNN link predictors surpass the hand-crafted-feature baseline AUC of 0.76 [5]. The paper argues that systemic risk cannot be managed node-by-node: it must be predicted at the level of the network graph.},
      keywords = {cascading risk prediction, disruption propagation, Graph neural networks, link prediction, multi-tier supply chains, ripple effect, supply chain resilience, supply chain visibility},
      month = {January},
      doi = {https://doi.org/10.64388/ire1725050}
  }