SKU Clustering for Supply Chain Planning Efficiency

Globalized companies seek growth while dealing with more complex and compelling challenges such as economic volatility, fluctuating commodity prices, supply-chain inefficiencies and increasing customer expectations. While companies cannot control all of these challenges, there is much they can do to remain competitive. Companies can gain competitive edge through improved demand forecasting and efficient inventory management. SKU segmentation is a concept that intends to demonstate that there is a economic benefit behind treating and handling some products differently from another. Our thesis optimized SKU segmentation for a global CPG and restaurant brand. This aided inventory managers and supply planners adequately assess the varying needs of diverse products, to cluster them according to comparable needs, to reduce supply chain costs and optimize their supply chain. To explore this problem, we analyzed 53 weeks of forecast and demand data for over 15,000 SKUs. Utilizing a variety of clustering techniques, we identified a more cost-effective clustering strategy for the subject case. We analyzed the comparative costs between our theoretical classification and the actual classification used by the subject case study. Once we identified the disconnect, we calculated the incurred costs for being out of the optimal solution. This included both the effect of safety stock and the stock out costs. Our research created new insights into the comparable cost of under-forecasting and over-forecasting on safety stock and customer service level. Thesis Supervisor: Dr. Edgar Blanco Title: Research Director, Center for Transportation and Logistics Executive Director, MIT SCALE Latin America