A Data-Driven Supply Chain Risk Early Warning Mechanism: An Integrated Framework of Multi-Source Data Fusion, Knowledge Graph, and Digital Twin
DOI: https://doi.org/10.62517/jbdc.202601410
Author(s)
Ruoqian Yang*, Wenxia Wang, Ding Xiao
Affiliation(s)
School of Economics and Management, Zhongshan Polytechnic, Zhongshan, Guangdong, China
*Corresponding Author
Abstract
Persistent overstock-shortage paradoxes, high logistics costs and black-swan disruptions expose the limits of experience-based supply chain risk identification. This paper develops a data-driven early warning mechanism built on an integrated three-layer architecture. A multi-source data governance framework first breaks down the silos among Internet-of-Things sensing, enterprise ERP/WMS/TMS records, market intelligence and geospatial data, and a deep-learning repair module safeguards data quality. A spatiotemporal knowledge graph of the supply chain network is then constructed to extract risk features and cascading propagation paths automatically. On this basis, an LSTM-Autoencoder detects anomalies, a Pareto-based multi-objective model grades risk situations, and a digital twin simulates response scenarios, together answering whether a risk exists, how severe it is and what should be done. A 36-month empirical study of 30 manufacturing, retail and e-commerce firms in Zhongshan, China, reports warning accuracy of 85.7%-90.2%, an average lead time of 14.2-17.8 days and logistics management cost savings of 10%-18%. The mechanism is further converted into virtual simulation resources for vocational logistics education.
Keywords
Supply Chain Risk; Data-Driven; Risk Early Warning; Knowledge Graph; Digital Twin; Supply Chain Resilience.
References
[1]CHRISTOPHER M, PECK H. Building the resilient supply chain. The International Journal of Logistics Management, 2004, 15(2): 1-14.
[2]DOLGUI A, IVANOV D, SOKOLOV B. Ripple effect in the supply chain: an analysis and recent literature. International Journal of Production Research, 2018, 56(1-2): 414-430.
[3]IVANOV D, DOLGUI A. Viability of intertwined supply networks: extending the supply chain resilience angles towards survivability. International Journal of Production Research, 2020, 58(10): 2904-2915.
[4]BARYANNIS G, VALIDI S, DANI S, et al. Supply chain risk management and artificial intelligence: state of the art and future research directions. International Journal of Production Research, 2019, 57(7): 2179-2202.
[5]WANG G, GUNASEKARAN A, NGAI E W T, et al. Big data analytics in logistics and supply chain management: certain investigations for research and applications. International Journal of Production Economics, 2016, 176: 98-110.
[6]BEN-DAYA M, HASSINI E, BAHROUN Z. Internet of things and supply chain management: a literature review. International Journal of Production Research, 2019, 57(15-16): 4719-4742.
[7]ZHONG R Y, NEWMAN S T, HUANG G Q, et al. Big data for supply chain management in the service and manufacturing sectors: challenges, opportunities, and future perspectives. Computers & Industrial Engineering, 2016, 101: 572-591.
[8]KOSASIH E E, BRINTRUP A. Towards trustworthy AI for link prediction in supply chain knowledge graph: a neurosymbolic reasoning approach. International Journal of Production Research, 2024, 62(15): 5123-5145.
[9]BARYANNIS G, DANI S, ANTONIOU G. Predicting supply chain risks using machine learning: the trade-off between performance and interpretability. Future Generation Computer Systems, 2019, 101: 993-1004.
[10]HOSSEINI S, IVANOV D, DOLGUI A. Review of quantitative methods for supply chain resilience analysis. Transportation Research Part E: Logistics and Transportation Review, 2019, 125: 285-307.
[11]FAHIMNIA B, TANG C S, DAVARZANI H, et al. Quantitative models for managing supply chain risks: a review. European Journal of Operational Research, 2015, 247(1): 1-15.
[12]CHOPRA S, SODHI M S. Managing risk to avoid supply-chain breakdown. MIT Sloan Management Review, 2004, 46(1): 53-61.
[13]HOCHREITER S, SCHMIDHUBER J. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780.
[14]HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. London: ACM, 2018: 387-395.
[15]AUDIBERT J, MICHIARDI P, GUYARD F, et al. USAD: unsupervised anomaly detection on multivariate time series//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Virtual Event: ACM, 2020: 3395-3404.
[16]SIMCHI-LEVI D, SCHMIDT W, WEI Y, et al. Identifying risks and mitigating disruptions in the automotive supply chain. Interfaces, 2015, 45(5): 375-390.
[17]MIN H. Artificial intelligence in supply chain management: theory and applications. International Journal of Logistics: Research and Applications, 2010, 13(1): 13-39.
[18]TAO F, ZHANG H, LIU A, et al. Digital twin in industry: state-of-the-art. IEEE Transactions on Industrial Informatics, 2019, 15(4): 2405-2415.
[19]IVANOV D, DOLGUI A, DAS A, et al. Digital supply chain twins: managing the ripple effect, resilience and disruption risks by data-driven optimization, simulation and visibility. International Journal of Production Research, 2019, 57(3): 829-844.
[20]KRITZINGER W, KARNER M, TRAAR G, et al. Digital twin in manufacturing: a categorical literature review and classification. IFAC-PapersOnLine, 2018, 51(11): 1016-1022.
[21]DOLGUI A, IVANOV D. Ripple effect and supply chain disruption management: new trends and research directions. International Journal of Production Research, 2021, 59(1): 102-109.
[22]LIU F T, TING K M, ZHOU Z H. Isolation forest//Proceedings of the 8th IEEE International Conference on Data Mining. Pisa: IEEE, 2008: 413-422.
[23]ZHAO Y, NASRULLAH Z, LI Z. PyOD: a python toolbox for scalable outlier detection. Journal of Machine Learning Research, 2019, 20(96): 1-7.
[24]DEB K, PRATAP A, AGARWAL S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
[25]SAATY T L. How to make a decision: the analytic hierarchy process. European Journal of Operational Research, 1990, 48(1): 9-26.
[26]Ivanov, D. (2023). "Intelligent digital twin (IDT) for supply chain stress-testing, resilience, and viability." International Journal of Production Economics.
[27]Cao, F., Liu, L., & Song, W. (2025). "Reducing sustainable supply chain risks: a digital technology-enabled risk management framework for ESG-oriented engineering procurement." IET Collaborative Intelligent Manufacturing.
[28]Liu, L., Chen, Y., Yang, J., & Yang, C.-F. (2025). "IoT-driven Dynamic Risk Management in Supply Chain Finance: A Multitechnology Fusion Framework and Collaborative Implementation Strategies." Sensors and Materials.
[29]Onebunne, T. C., & Adepoju, A. S. (2025)."Adaptive Inventory Management in Global Supply Chains Using Digital Twins and Reinforcement Learning for Disruption Resilience and Sustainability." International Journal of Advanced and Innovative Research.