An efficient and accurate supply chain can drive significant business benefits for companies. However, achieving an optimal supply to match demand is difficult, and made more challenging as external factors such as supplier decommits, market factors, government regulations, part unavailability, price fluctuations and lead times all influence the outcome. This variance is further compounded by the inconsistent ordering of parts, both in order timing and in order quantity.
In this paper, we propose a novel forecasting method that deviates from long-term averages and relies on time-series models, which are aggregated and optimized.
An optimized ensemble model provides for higher accuracy (increase of over 20%) in both cycle stock forecast and safety stock requirements, resulting in an overall reduction in capital costs (by over 25%).
Download the White Paper