🤖 AI Summary
To address the critical challenge of early warning for supply disruptions among Tier-1 automotive suppliers, this work constructs a large-scale industrial dataset comprising over 500,000 heterogeneous multivariate time series, incorporating Factory Physics–informed features such as production capacity, inventory levels, and equipment utilization. We propose a novel joint modeling framework integrating Attention-based Seq2Seq forecasting with survival analysis, augmented by neural embeddings to capture supplier heterogeneity and SHAP-based interpretability for diagnostic transparency—thereby overcoming key limitations of black-box opacity and poor generalizability in industrial time-series prediction. Evaluated across five Ford North American manufacturing plants in QA testing, the model achieves 0.85 precision and 0.80 recall, significantly enhancing early detection of supply interruptions and supporting higher-quality, timely operational decision-making.
📝 Abstract
Operational disruptions can significantly impact companies performance. Ford, with its 37 plants globally, uses 17 billion parts annually to manufacture six million cars and trucks. With up to ten tiers of suppliers between the company and raw materials, any extended disruption in this supply chain can cause substantial financial losses. Therefore, the ability to forecast and identify such disruptions early is crucial for maintaining seamless operations. In this study, we demonstrate how we construct a dataset consisting of many multivariate time series to forecast first-tier supply chain disruptions, utilizing features related to capacity, inventory, utilization, and processing, as outlined in the classical Factory Physics framework. This dataset is technically challenging due to its vast scale of over five hundred thousand time series. Furthermore, these time series, while exhibiting certain similarities, also display heterogeneity within specific subgroups. To address these challenges, we propose a novel methodology that integrates an enhanced Attention Sequence to Sequence Deep Learning architecture, using Neural Network Embeddings to model group effects, with a Survival Analysis model. This model is designed to learn intricate heterogeneous data patterns related to operational disruptions. Our model has demonstrated a strong performance, achieving 0.85 precision and 0.8 recall during the Quality Assurance (QA) phase across Ford's five North American plants. Additionally, to address the common criticism of Machine Learning models as black boxes, we show how the SHAP framework can be used to generate feature importance from the model predictions. It offers valuable insights that can lead to actionable strategies and highlights the potential of advanced machine learning for managing and mitigating supply chain risks in the automotive industry.