Client
FMCG Manufacturer
Industry
CPG
Solution
FMCG ManufacturerA leading spirits manufacturer based in the USA, with over $14 billion in revenue, faced significant challenges due to their complex manufacturing processes and vast global operations, spanning more than 20 manufacturing facilities and 70 warehouses. The client was grappling with substantial financial losses, as stockouts and high inventory holding costs (IHC) contributed to a 20% dip in business performance.
Complex Operation Management
Outdated Forecasting Tools
$200M Financial Losses
The core issue stemmed from an outdated demand forecasting solution that followed a one-size-fits-all approach and failed to incorporate critical marketing signals. This inaccuracy led to excessive stockpile accumulation for certain SKUs and frequent stockouts for others, resulting in combined losses of over $200 million. To mitigate these challenges, the client required a solution capable of enhancing forecasting accuracy by at least 20%.
Quantzig began by analyzing the demand signals for various SKUs, identifying patterns and discrepancies that impacted forecasting accuracy. This detailed analysis allowed Quantzig to develop a robust SKU classification framework, which served as the foundation for a more tailored forecasting approach.
Building on this framework, Quantzig deployed advanced machine-learning algorithms to interpret the demand signals for each SKU. By running multiple algorithms for every SKU, the solution identified nuanced demand trends that were previously overlooked, ensuring that each SKU received a customized model rather than relying on a one-size-fits-all approach.
To further enhance efficiency and accuracy, Quantzig automated the calculation of the Mean Absolute Percentage Error (MAPE) for each model, which streamlined the process of selecting the best-fit model for each SKU, guaranteeing the highest level of forecasting precision and reliability.
Implementing Quantzig's solution led to a remarkable 75–90% improvement in forecast accuracy, effectively addressing the challenges of stockouts and excess inventory. Additionally, the forecasting process became 80% faster, enabling quicker, data-driven decision-making. These advancements significantly improved production planning, optimized resource allocation, reduced costs, and enhanced overall operational efficiency.
