Abstract

Penina ORENSTEIN, Timothy Jason STALKER

Abstract : Over the past decade or so, businesses, have amassed exponentially growing amounts of data in large databases but the data's hidden value, the potential to predict relationships between supply and demand, has largely gone untapped. In today's technological era, smart supply chains are not only capturing vast quantities of data, they are converting this information into knowledge which is subsequently being infused back into the system. When data is transformed into information, businesses can make informed decisions, reduce costs in the supply chain and improve overall productivity. This paper considers a two-stage supply chain in which a single supplier, the Green Flavor Tea (GFT) ships a custom blend of pre-mixed tea compound to a single customer, Best Tea (BT). BT uses the compound to produce a particular brand of liquid green tea which is shipped in containers of varying sizes. Order fulfillment is contingent on inventory levels, which are measured only upon receipt of a sales order. Preliminary data analysis shows that there is a consistent gap in perceived inventory levels vs. what is actually being held -- the discrepancy is at times both favorable and unfavorable. When inventory levels are unfavorable, the supplier must outsource materials from competitive firms, thereby eroding sensitive profit margins. By adopting a "hierarchical approach" by which we mean a comparison of the data at the strategic, tactical and operational levels, the authors highlight the discrepancies in supplier-customer inventory levels as well as the seasonal effects in the data. The analysis concentrates on the feedback loop between the supplier and the customer and reveals a lack of integration between the parties. The authors compare the performance of several forecasting methods which appropriately account for seasonality with the aim to improve inventory planning between GFT and BT. This ultimately will lead to an alignment of supply and demand. The analysis concludes with some recommendations as to how to implement the collaborative forecasting model with the supply chain partners.

Keywords : Supply Chains; Collaborative Forecasting; Inventory Planning

Year : 2011
Issue : 1
Volume : 4