Optimizing inventory levels using financial, lifecycle and forecast variance data

Abstract

Significant inventory write-offs have recently plagued ATI Technologies, a world leader in graphics and media processors. ATI's product-centric culture has long deterred attention from supply chain efficiency. Given that manufacturing lead time exceeds customer order lead time for its semiconductors, ATI relies heavily on their demand forecasting team to instigate supply chain activities. The PC business unit forecasting team translates market information into product-line forecast and also sets finished goods inventory levels intended to offset demand uncertainty. Today's inventory decisions are made in response to customer escalations, often ignoring financial implications. To add necessary rigor when setting these inventory levels, this thesis presents a model using wafer and unit cost, profit margin, product lifecycle stage and historical forecast error to categorize products into inventory risk levels. The resultant risk levels become a critical input to monthly demand-supply meetings with marketing, operations and senior executives - the outcome of which are wafer orders and assembly and test plans at the world's largest contract foundries and subcontractors. Finally, the 2006 acquisition of ATI by Advanced Micro Devices (AMD) offers unforeseen flexibility, scale and challenges to the outsourced semiconductor supply chain.