Root Cause Attribution of Delivery Risks via Causal Discovery with Reinforcement Learning
It addresses the challenge of spurious correlations in complex supply chains for improving operational efficiency and profitability, though it appears incremental as it combines existing techniques in a novel way.
This paper tackles the problem of identifying root causes of delivery risks in supply chains by integrating causal discovery with reinforcement learning, resulting in accurate identification of key drivers like shipping mode and delivery status from a real-world dataset.
This paper presents a novel approach to root cause attribution of delivery risks within supply chains by integrating causal discovery with reinforcement learning. As supply chains become increasingly complex, traditional methods of root cause analysis struggle to capture the intricate interrelationships between various factors, often leading to spurious correlations and suboptimal decision-making. Our approach addresses these challenges by leveraging causal discovery to identify the true causal relationships between operational variables, and reinforcement learning to iteratively refine the causal graph. This method enables the accurate identification of key drivers of late deliveries, such as shipping mode and delivery status, and provides actionable insights for optimizing supply chain performance. We apply our approach to a real-world supply chain dataset, demonstrating its effectiveness in uncovering the underlying causes of delivery delays and offering strategies for mitigating these risks. The findings have significant implications for improving operational efficiency, customer satisfaction, and overall profitability within supply chains.