“Enhancing Forecast Accuracy and Disruption Prevention in the Supply Chain: A Case Study at STIGA S.p.A.”

This study investigates procurement planning performance at STIGA S.p.A., an Italian multinational garden equipment manufacturer, and proposes a data-driven improvement framework to address the structural misalignment between purchasing planning and procurement execution. The empirical analysis is based on 169,321 procurement records from the SAP Business Intelligence system covering seven material categories and €265,356,422 in total procurement value. A systematic planning-execution gap is identified as the central operational problem — a recognised procurement-level manifestation of the bullwhip effect (Lee et al., 1997; Chopra and Meindl, 2021), compounded by the absence of safety stock logic in SAP MRP and static lead-time parameters that do not reflect empirical supplier variability. The baseline procurement service level is estimated at 32.9%, substantially below the 80–95% manufacturing benchmark. On-Time Delivery against original commitment dates stands at 18.0% across the portfolio, with Engines and Power Components recording only 5% punctuality. Electronics and Electric Motors carries a mean lead time of 93.8 days, past-due exposure totals €3,881,924, and the Loncin Motor Group — representing 17.8% of total spend — presents a compound risk of chronic delays and severe financial vulnerability. Monte Carlo simulation (10,000 iterations, empirically calibrated from SAP BI data) evaluates four improvement scenarios. The results confirm that no single intervention — forecasting improvement, safety stock, or lead-time management alone — is sufficient. Only a combined intervention of decoupled purchasing logic, dynamic safety stock, and updated lead-time parameters achieves a service level of 80.4%, a 47.5 percentage-point improvement over baseline. The study contributes empirical evidence that these three levers must be addressed simultaneously in seasonal manufacturing procurement, and proposes a replicable five-layer SAP BI monitoring architecture and a three-dimensional supplier risk matrix integrating spend concentration, delivery performance, and financial health indicators.

This study investigates procurement planning performance at STIGA S.p.A., an Italian multinational garden equipment manufacturer, and proposes a data-driven improvement framework to address the structural misalignment between purchasing planning and procurement execution. The empirical analysis is based on 169,321 procurement records from the SAP Business Intelligence system covering seven material categories and €265,356,422 in total procurement value. A systematic planning-execution gap is identified as the central operational problem — a recognised procurement-level manifestation of the bullwhip effect (Lee et al., 1997; Chopra and Meindl, 2021), compounded by the absence of safety stock logic in SAP MRP and static lead-time parameters that do not reflect empirical supplier variability. The baseline procurement service level is estimated at 32.9%, substantially below the 80–95% manufacturing benchmark. On-Time Delivery against original commitment dates stands at 18.0% across the portfolio, with Engines and Power Components recording only 5% punctuality. Electronics and Electric Motors carries a mean lead time of 93.8 days, past-due exposure totals €3,881,924, and the Loncin Motor Group — representing 17.8% of total spend — presents a compound risk of chronic delays and severe financial vulnerability. Monte Carlo simulation (10,000 iterations, empirically calibrated from SAP BI data) evaluates four improvement scenarios. The results confirm that no single intervention — forecasting improvement, safety stock, or lead-time management alone — is sufficient. Only a combined intervention of decoupled purchasing logic, dynamic safety stock, and updated lead-time parameters achieves a service level of 80.4%, a 47.5 percentage-point improvement over baseline. The study contributes empirical evidence that these three levers must be addressed simultaneously in seasonal manufacturing procurement, and proposes a replicable five-layer SAP BI monitoring architecture and a three-dimensional supplier risk matrix integrating spend concentration, delivery performance, and financial health indicators. This thesis examines the role of purchasing forecasting in enhancing supply chain performance through a case study conducted at STIGA S.p.A., a multinational manufacturer operating in a highly seasonal industry. The study adopts a mixed-method approach that combines quantitative analysis of purchasing and supplier data extracted from SAP BI with Excel-based evaluation of forecast accuracy and lead-time variability. In addition, a supply chain simulation model is developed using anyLogistix to assess the impact of different forecasting and sourcing scenarios under conditions of supplier disruption. The analysis indicates that improvements in purchasing forecast accuracy are associated with reduced material shortages and enhanced service levels. Simulation-based scenario analysis further suggests that integrating forecast improvements with risk-aware inventory and sourcing policies can strengthen supply chain resilience. The findings are expected to provide practical insights for procurement professionals and contribute to the literature on data-driven purchasing forecasting and disruption management.