Unlocking Real-Time Decision-Making in Warehouses: A machine learning-based forecasting and alerting system for cycle time prediction

In highly automated warehouses characterized by unpredictable demand, timely decision-making is critical to maintaining operational efficiency. This study proposes a forecasting and alerting system for real-time warehouse management. The system utilizes a Machine Learning (ML)-based predictive model to forecast picking order tardiness using Warehouse Management System data, complemented by a real-time alerting mechanism to support operators in in making informed short-term decisions. A case study conducted in a Shuttle-Based Storage and Retrieval Systems (SBS/RS) of a tire distribution company validates the system's effectiveness. Particularly, several ML techniques were tested to find the best forecasting model, leveraging a set of predictors tailored to the characteristics of the warehouse. Simulation with real data demonstrates significant reductions of peak cycle times and in total cycle time.