Data-Driven Warehouse Performance and Workforce Planning: Framework for Operational Efficiency and Headcount Forecasting

Warehouse operations rely on a close alignment between the volume of work generated by day-to-day activity and the available labor to complete it, but these two dimensions do not always move in together. Commercial metrics such as sales are frequently used, implicitly or explicitly, as a proxy for personnel requirements, despite the fact that operational workload might differ significantly from commercial trends. This thesis explores that relationship at Experica, an automotive aftermarket company, with a focus on its major logistics platform in Padova. Prior to this study, the company's operational and workforce data were stored in separate systems, limiting management's understanding of how labor capacity corresponds to the activity it supports. This thesis addresses the gap in two stages. The first creates an integrated analytical framework that combines operational, commercial, and workforce data to characterize how warehouse activity, productivity, and staffing have changed over the study period and assess how well they have remained aligned. The second builds on this descriptive foundation to create a predictive approach for forecasting future workforce requirements using past patterns, shifting the focus from explanation to planning support. The data indicate that workload and labor capacity have not moved in tight alignment over the analysis period, and given the limited historical horizon and recursive forecast uncertainty, the resulting staffing estimates are interpreted as planning scenarios rather than fixed staffing requirements. Taken together, the study provides a diagnostic account of how workload and labor capacity interacted at Experica, as well as a practical foundation for more informed, data-driven workforce planning, with implications that may extend to other labor-intensive warehouse operations facing similar challenges in aligning demand and staffing.