Abstract
AbstractIn this work, we investigate the implications of commodity price uncertainty for optimal procurement and inventory control decisions. While the existing literature typically relies on the full information paradigm, i.e., optimizing procurement and inventory decisions under full information of the underlying stochastic price process, we develop and test different data-driven approaches that optimize decisions under very limited statistical model assumptions. Our results are data-driven policies and decision rules that can support commodity procurement managers, inventory managers as well as commodity merchants. We furthermore test all optimization models based on real data from different commodity classes (i.e., metals, energy and agricultural).This paper is a summary of the author’s dissertation (Mandl C. (2019). Optimal Procurement and Inventory Control in Volatile Commodity Markets - Advances in Stochastic and Data-Driven Optimization, [1]).KeywordsPrice uncertaintyProcurementInventory controlData-driven optimizationMachine learning
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call