FMCG Demand Forecasting
€2.4M saved annually
Client Context
An FMCG company managing 4,000+ SKUs across 12 warehouses supplying major European retailers. Demand planning relied on spreadsheet-based forecasts updated monthly.
The Challenge
Stockouts were costing the company key shelf positions with retailers. Simultaneously, excess inventory tied up capital in slow-moving SKUs. The planning team couldn’t account for promotional impacts, weather effects, or economic indicators at SKU level.
Our Approach
We built a demand forecasting system using Temporal Fusion Transformers that incorporates sales history, promotional calendars, weather data, and macroeconomic indicators. The system generates daily forecasts at SKU-warehouse level with automatic alerts when demand deviates from predictions.
Timeline: 16 weeks
The Results
- Forecast accuracy improved 23%
- Stockouts reduced 35%
- Holding costs reduced by €2.4M annually
- Planning team now manages by exception rather than manually forecasting
Facing a similar challenge?
Let’s talk about how we can help your organisation achieve similar results.