Supply chain agility has been receiving a lot of attention in recent literature as a way for organizations to become more responsive to change and improve customer service levels. However, agility is typically dealt with qualitatively, and organizations are usually unsure of the steps to take to improve their agility and the customer service level to target. This research studies supply chain agility based on a case study of Intel Corporation, a large semiconductor manufacturer. Here, agility is defined as the ability to satisfy customer demands by reacting effectively to changes in market stimuli. Reacting effectively does not mean reacting to every change in supply or demand. Doing so means increasing supply chain variability unnecessarily, which is amplified by the bullwhip effect. The essence of supply chain agility is determining the degree to which variability should be managed through artificial means such as safety stock, and appropriate triggers for changing production levels and inventory targets. The purpose of this research is to examine factors that influence supply chain agility and identify a cost-effective plan for achieving it. The first phase addresses the problem of identifying target inventory and customer service levels based on regression analysis of historical data and financial analysis of inventory holding costs and stock-out costs. The impact of three factors (forecast error, order lead-time, and demand variability) on the relationship between inventory and customer service level is also examined. The second phase of the research evaluates strategies for production and inventory control with the goal of finding the appropriate trade-off between minimizing cost (of holding inventory and stock-outs) and minimizing variability. Control policies based on the Exponentially Weighted Moving Average (EWMA) control chart with control limits on demand forecasts are proposed to detect when tighter control of processes is necessary. A Monte Carlo supply chain simulation is used to evaluate the performance of these policies under various levels of forecast error and demand variability. Results indicate that several control chart-based policies outperform Intel's current planning policy in terms of cost without significantly increasing variability. The selection of the appropriate policy must be based on the decision-makers' desire to minimize cost compared to the desire to minimize variability, as each policy results in a trade-off between these two objectives.
| Identifer | oai:union.ndltd.org:ucf.edu/oai:stars.library.ucf.edu:etd-1573 |
| Date | 01 January 2005 |
| Creators | Jeffery, Mariah |
| Publisher | STARS |
| Source Sets | University of Central Florida |
| Language | English |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Electronic Theses and Dissertations |
Page generated in 0.0021 seconds