End-to-End Supply Chain Resilience Management using Deep Learning, Survival Analysis, and Explainable Artificial Intelligence

Xingyu Li, Vasiliy Krivtsov*, Chaoye Pan, Aydin Nassehi, Robert X. Gao, Dmitry Ivanov

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)peer-review

Abstract

This study introduces a data-centric framework for end-to-end supply chain resilience management. With major disruptions such as pandemics profoundly affect- ing industries and regions, a wealth of data capturing diverse disruption scenarios has emerged. This presents an opportunity to correlate deviations in organizational operations with disruption outcomes, facilitating the identification of risk sources and the formulation of effective mitigation strategies for future disruptive events. Utilizing deep learning, survival analysis, and explainable artificial intelligence, the research represents a pioneering advancement in translating readily accessible organizational data into forecasts of disruption risks and sources, differing from traditional model-centric methodologies.

The application of this framework to a real-world scenario based on a U.S. auto- motive manufacturer resulted in accurately predicting the time-to-survive for critical parts, with a prediction error of under 20 days across a year. Notably, the model achieved a 50% reduction in error rates for near-term and long-term predictions com- pared to the best-performing alternative models, affirming its efficacy in utilizing organizational data for evaluating production risks and inferring underlying supply chain risks. Our findings underscore the framework’s ability to effectively address the complexities of global supply chain disruptions and unknown-unknown uncertainties by harnessing insights gleaned from detailed historical data on industry-wide disruptions. This accumulated knowledge enables real-time risk identification and assessment, empowering organizations to deploy timely and targeted risk mitigation strategies for enhancing overall supply chain resilience.
Original languageEnglish
JournalInternational Journal of Production Research
Publication statusAccepted/In press - 17 Apr 2024

Fingerprint

Dive into the research topics of 'End-to-End Supply Chain Resilience Management using Deep Learning, Survival Analysis, and Explainable Artificial Intelligence'. Together they form a unique fingerprint.

Cite this