Supply chain disruptions and volatile demand pose significant challenges to the UK automotive industry, which relies heavily on Just-In-Time (JIT) manufacturing. While qualitative studies highlight the potential of integrating Artificial Intelligence (AI) with traditional optimization, a formal, quantitative demonstration of this synergy is lacking. This paper introduces a novel stochastic learning-optimization framework that integrates Bayesian inference with inventory optimization for supply chain management (SCM). We model a two-echelon inventory system subject to stochastic demand and supply disruptions, comparing a traditional static optimization policy against an adaptive policy where Bayesian learning continuously updates parameter estimates to inform stochastic optimization. Our simulations over 365 periods across three operational scenarios demonstrate that the integrated approach achieves 7.4\% cost reduction in stable environments and 5.7\% improvement during supply disruptions, while revealing important limitations during sudden demand shocks due to the inherent conservatism of Bayesian updating. This work provides mathematical validation for practitioner observations and establishes a formal framework for understanding AI-driven supply chain resilience, while identifying critical boundary conditions for successful implementation.

The COVID-19 pandemic has highlighted the importance of supply chains and the role of digital management to react to dynamic changes in the environment. In this work, we focus on developing dynamic inventory ordering policies for a multi-echelon, i.e. multi-stage, supply chain. Traditional inventory optimization methods aim to determine a static reordering policy. Thus, these policies are not able to adjust to dynamic changes such as those observed during the COVID-19 crisis. On the other hand, conventional strategies offer the advantage of being interpretable, which is a crucial feature for supply chain managers in order to communicate decisions to their stakeholders. To address this limitation, we propose an interpretable reinforcement learning approach that aims to be as interpretable as the traditional static policies while being as flexible and environment-agnostic as other deep learning-based reinforcement learning solutions. We propose to use Neural Additive Models as an interpretable dynamic policy of a reinforcement learning agent, showing that this approach is competitive with a standard full connected policy. Finally, we use the interpretability property to gain insights into a complex ordering strategy for a simple, linear three-echelon inventory supply chain.

"What you do today can improve all your tomorrows." The new omnichannel world has not only affected how retailers engage with their customers, but also how retailers plan their inventory. For many retailers, inventory has become quite undisciplined, coming and going from new and different channels at all hours. And that creates a lot of challenges, because if you remember from our previous articles, retailers generally measure omnichannel demand two ways. Either they count everything as retail demand for whatever location fulfills an order or sells directly to a customer, or they look at in-store sales as one demand stream and e-commerce as another.

While data may'want to be free' from a societal perspective, from a company perspective, private data, intellectual property and trade secrets are proprietary knowledge. Such knowledge, mated with domain expertise and smart execution, can be a competitive market advantage, which in a well-run, lean, continuously-improving operation, will ultimately provide market power. To protect data from leaking out, via both external and internal influences, a comprehensive, multi-layered security framework is always essential. And some of the first traces of security breaches, both physical and cyber, can be picked up in the minute signals hidden in the tea-leaves of operations. While IT (Information Technology) typically doesn't have the tools, budget or domain expertise to pick-up such signals across Operations, OT (Operations Technology) conversely has such knowledge but not the time or resources, as they're constantly focused on keeping operations up and running smoothly for the next hour, shift or day.