Author(s)

YuChen Li

Affiliation(s)

School of Computer Science, Carnegie Mellon University, USA.

Corresponding Author

YuChen Li

ABSTRACT

Supply chain disruptions have emerged as critical challenges in global operations, with economic impacts exceeding trillions of dollars annually. Traditional prediction methods often fail to capture complex causal relationships and counterfactual scenarios essential for proactive risk management. This paper proposes a novel Causal Graph Neural Network (C-GNN) framework that integrates counterfactual reasoning with multimodal external signals for supply chain disruption prediction. The framework leverages directed acyclic graphs to represent causal dependencies among supply chain entities while incorporating diverse data sources including financial indicators, geopolitical events, and environmental factors. Experimental results demonstrate that our approach achieves superior prediction accuracy compared to conventional methods, with the ability to generate actionable counterfactual explanations for potential disruptions. The proposed framework offers supply chain managers interpretable insights for scenario planning and proactive intervention strategies, contributing to enhanced supply chain resilience in increasingly volatile global markets.

KEYWORDS

Supply chain disruption; Counterfactual reasoning; Causal inference; Graph neural networks; Multimodal learning; Risk prediction; Supply chain resilience

CITE THIS PAPER

YuChen Li. Counterfactual reasoning in supply chain disruption prediction: a causal graph neural network approach with multimodal external signals. Social Science and Management. 2025, 2(4): 20-28. DOI: https://doi.org/10.61784/ssm3066.

REFERENCES

[1] Singh S, Kumar R, Panchal R, et al. Impact of COVID-19 on logistics systems and disruptions in food supply chain. Int J Prod Res, 2021, 59(7): 1993-2008.

[2] Ma Z, Chen X, Sun T, et al. Blockchain-based zero-trust supply chain security integrated with deep reinforcement learning for inventory optimization. Future Internet, 2024, 16(5): 163.

[3] Sun T, Yang J, Li J, et al. Enhancing auto insurance risk evaluation with transformer and SHAP. IEEE Access, 2024, 12, 116546-116557. DOI: 10.1109/ACCESS.2024.3446179.

[4] Zheng G, Brintrup A, et al. A machine learning approach for enhancing supply chain visibility with graph-based learning. Supply Chain Analytics, 2025, 11, 100135.

[5] Wang Y, Ding G, Zeng Z, et al. Causal-aware multimodal transformer for supply chain demand forecasting: integrating text, time series, and satellite imagery. IEEE Access, 2025, 13, 176813-176829. DOI: 10.1109/ACCESS.2025.3619552.

[6] Verma S, Boonsanong V, Hoang M, et al. Counterfactual explanations and algorithmic recourses for machine learning: a review. ACM Computing Surveys, 2024, 56(12): 1-42.

[7] Maheshwari S, Gautam P, Jaggi C K. Role of big data analytics in supply chain management: current trends and future perspectives. Int J Prod Res, 2021, 59(6): 1875-1900.

[8] Xu S, Zhang X, Feng L, et al. Disruption risks in supply chain management: a literature review based on bibliometric analysis. Int J Prod Res, 2020, 58(11): 3508-3526.

[9] Paul S K, Chowdhury P, Moktadir M A, et al. Supply chain recovery challenges in the wake of COVID-19 pandemic. J Bus Res, 2021, 136, 316-329.

[10] Ivanov D, Dolgui A. Viability of intertwined supply networks: extending the supply chain resilience angles towards survivability. Int J Prod Res, 2020, 58(10): 2904-2915.

[11] Aziz A, Kosasih E E, Griffiths R R, et al. Data considerations in graph representation learning for supply chain networks. arXiv preprint. 2021. DOI: https://doi.org/10.48550/arXiv.2107.10609.

[12] Giannoccaro I, Iftikhar A. Mitigating ripple effect in supply networks: the effect of trust and topology on resilience. Int J Prod Res, 2022, 60(4): 1178-1195.

[13] Li Y, Chen K, Collignon S, et al. Ripple effect in the supply chain network: forward and backward disruption propagation, network health and firm vulnerability. Eur J Oper Res, 2021, 291(3): 1117-1131.

[14] Bag S, Wood L C, Xu L, et al. Big data analytics as an operational excellence approach to enhance sustainable supply chain performance. Resour Conserv Recycl, 2020, 153, 104559.

[15] Aamer A, Yani L P E, Priyatna I M A. Data analytics in the supply chain management: review of machine learning applications in demand forecasting. Oper Supply Chain Manag, 2020, 14(1): 1-13.

[16] Li B, Pi D. Network representation learning: a systematic literature review. Neural Comput Appl, 2020, 32(21): 16647-16679.

[17] Brintrup A, Kosasih E E, Aziz A, et al. A machine learning approach for predicting hidden links in supply chains with graph neural networks. Int J Prod Res, 2022, 60(17): 5380-5393.

[18] Han K. Applying graph neural network to SupplyGraph for supply chain network. arXiv preprint. 2024. DOI:  https://doi.org/10.48550/arXiv.2408.14501.

[19] Wang Y, Zhang H, Liu X, et al. Graph neural Poisson models for supply chain relationship forecasting. arXiv preprint. 2025 DOI: https://doi.org/10.48550/arXiv.2508.12044.

[20] Cao W, Mai N T, Liu W. Adaptive knowledge assessment via symmetric hierarchical Bayesian neural networks with graph symmetry-aware concept dependencies. Symmetry, 2025, 17(8): 1332.

[21] Mai N T, Cao W, Liu W. Interpretable knowledge tracing via transformer-Bayesian hybrid networks: learning temporal dependencies and causal structures in educational data. Applied Sciences, 2025, 15(17): 9605.

[22] Guan D, Wang D, Hallegatte S, et al. Global supply-chain effects of COVID-19 control measures. Nat Hum Behav, 2020, 4(6): 577-587.

[23] Alessandria G, Khan S Y, Khederlarian A, et al. The aggregate effects of global and local supply chain disruptions: 2020–2022. J Int Econ, 2023, 146: 103740.

[24] Ge Y, Wang Y, Liu J, et al. GAN-enhanced implied volatility surface reconstruction for option pricing error mitigation. IEEE Access, 2025, 13, 176770-176787. DOI: 10.1109/ACCESS.2025.3619553.

[25] Zheng W, Liu W. Symmetry-aware transformers for asymmetric causal discovery in financial time series. Symmetry, 2025, 17(10): 1591.

[26] Tan Y, Wu B, Cao J, et al. LLaMA-UTP: knowledge-guided expert mixture for analyzing uncertain tax positions. IEEE Access, 2025, 13, 90637-90650. DOI: 10.1109/ACCESS.2025.3571502.

[27] Liu Y, Ren S, Wang X, et al. Temporal logical attention network for log-based anomaly detection in distributed systems. Sensors, 2024, 24(24): 7949.

[28] Karimi A H, Scholkopf B, Valera I. Algorithmic recourse: from counterfactual explanations to interventions. FAccT, 2021, 353-362.

[29] Mothilal R K, Sharma A, Tan C. Explaining machine learning classifiers through diverse counterfactual explanations. FAccT, 2020, 607-617.

[30] Ren S, Jin J, Niu G, et al. ARCS: adaptive reinforcement learning framework for automated cybersecurity incident response strategy optimization. Applied Sciences, 2025, 15(2): 951.

[31] Zhang Q, Chen S, Liu W. Balanced knowledge transfer in MTTL-ClinicalBERT: a symmetrical multi-task learning framework for clinical text classification. Symmetry, 2025, 17(6): 823.

[32] Chen S, Liu Y, Zhang Q, et al. Multi-distance spatial-temporal graph neural network for anomaly detection in blockchain transactions. Advanced Intelligent Systems, 2025, 2400898.

[33] Mai N T, Cao W, Wang Y. The global belonging support framework: enhancing equity and access for international graduate students. Journal of International Students, 2025, 15(9): 141-160.

[34] Hu X, Zhao X, Wang J, et al. Information-theoretic multi-scale geometric pre-training for enhanced molecular property prediction. PLoS One, 2025, 20(10): e0332640.

[35] Zhang H, Ge Y, Zhao X, et al. Hierarchical deep reinforcement learning for multi-objective integrated circuit physical layout optimization with congestion-aware reward shaping. IEEE Access, 2025, 13, 162533-162551. DOI: 10.1109/ACCESS.2025.3610615.

[36] Wang J, Zhang H, Wu B, et al. Symmetry-guided electric vehicles energy consumption optimization based on driver behavior and environmental factors: a reinforcement learning approach. Symmetry, 2025, 17(6): 930.

[37] Hu X, Zhao X, Liu W. Hierarchical sensing framework for polymer degradation monitoring: a physics-constrained reinforcement learning framework for programmable material discovery. Sensors, 2025, 25(14): 4479.

[38] Han X, Yang Y, Chen J, et al. Symmetry-aware credit risk modeling: a deep learning framework exploiting financial data balance and invariance. Symmetry, 2025, 17(3): 341. DOI: https://doi.org/10.3390/sym17030341.