Machine Learning-Based Control of Dual-Sourcing Inventory Systems

We examine a data-driven approach to dual-sourcing inventory systems under periodic review with uncertain demand, utilizing historical data. Different from conventional fixed-ordering policies, we advocate for a machine learning methodology to capture the dynamic behaviour of demand. We train machine learning models to predict demand for single-period and multi-period horizons. Subsequently, we utilize these predictions to manage and mitigate supply chain risk by ordering from two suppliers. One supplier, identified as the regular supplier, offers lower unit prices but longer delivery times. The other is the emergency supplier, which provides same-day delivery at a higher unit price. Through an extensive numerical study utilizing actual data from Rossmann drug stores and various machine learning models, we systematically assess the performance of prediction models. Further, we enhance the learning process of the machine learning models by incorporating inventory cost parameters into the training objective function. Specifically, we customize the learning objective, switching from mean squared error (i.e., non-guided models) to a single-period inventory cost function (i.e., guided models). This modification results in significant cost reduction in the dual-sourcing inventory system. Guiding the models offers robust data-driven solutions for complex sequential systems where fully integrating learning and decision-making is not feasible.