NetherlandsFood and restaurants2023 – ongoingHeineken
AI forecasting for trade promotions
Heineken's planning team reported better promotion forecasts with Visualfabriq
Problem
Heineken needed promotion forecasts that reflected differences between retailers and products. Manual predictions were the comparison for its AI models.
Approach
Heineken Netherlands used Visualfabriq's prediction software and tailored models to its planning needs. The team filtered data by retailer and product and used submodels for price elasticity and seasonality. It applied in-market and ex-factory forecasts alongside models for phasing volumes over time.
Results
No published figures
Takeaway
The models could be adjusted to specific retailer and product conditions. The reported improvement over manual forecasts had no published numerical accuracy measure.
Categories
- Size
- Large enterprise
- Industry
- Food and restaurants
- Business function
- Marketing and salesLogistics and supply chain
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
Visualfabriq described Heineken's use of configurable AI models for trade-promotion forecasts. Participants said the predictions outperformed manual forecasts, without publishing an error measure.
Full details are in the original sources.
