Despite comprising more than 50% of businesses Small and Medium Enterprises are seldomly the object of research and little attention is given to how widely accepted and proven methods of managing business are disseminated and implemented across them. The purpose of this study is to gain insight into the challenges faced by SMEs and how these challenges preclude and condition the policy design and methods deploying for Demand Forecasting for Inventory Management. In the quest to answer the research question of “How can a SME design a Demand Forecasting System for Inventory Management in the light of typical SME resource constraints?” this study follows one Danish SME in the Auto Industry aftermarket and builds a roadmap to deploy a Demand Forecasting system for Inventory Management considering the needs and resources available at the firm and largely generalizable across the SME ecosystem. The conceptual framework rests on previous studies and SME theory regarding general constraints, widely disseminated theory of demand forecasting and inventory control and builds on both to generate a guiding light to a satisfactory system of demand forecasting upon which inventory management policies rest. It studies several forms of demand data aggregation to determine how and when should forecasts be done and based on quantitative measures on said forecasts outlines an inventory management comprehensive policy for the case company that may contribute to a positive outcome in other SMEs facing similar challenges. Its findings are that most resource constraints described in SME literature are found at the case company and they indeed influence the decisions made at the policy design level. Based on these findings an extensive study on methods of aggregation and disaggregation and forecasting of time series was performed and revealed that while temporal aggregation was beneficial, cross-sectional aggregation was not desirable since decisions regarding inventory management are done at the SKU level and no satisfactory method of disaggregation was found. This dissertation then studies several solutions for replenishment policies based on forecasting error and performs an in-depth study of security stocks and centralized vs decentralized stocks to compare the nominal benefit accrued for the studied case company. Lastly the author proposes a generalizable roadmap solution for an SME to design and implement an Inventory Management system based on quantitative demand forecasting and discusses its limitations.
|Educations||MSc in Supply Chain Management , (Graduate Programme) Final Thesis|
|Number of pages||111|