DenmarkFood and restaurants2019 – ongoingArla Foods
AI milk-intake forecasting
Arla reduced milk forecasting from days to hours and reported 1.4% greater accuracy
Problem
Arla planned dairy operations around forecasts of milk arriving from farms. Producing those forecasts manually in spreadsheets took days.
Approach
Arla's data scientists developed an AI forecasting system with its IT supplier. The model used daily production data and seasonal factors. Arla implemented it across its European markets.
Results
Takeaway
The faster forecast supported planning across an existing supply network. Arla did not explain whether its accuracy improvement meant a relative percentage or percentage points.
Categories
- Size
- Large enterprise
- Industry
- Food and restaurants
- Business function
- Logistics and supply chain
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Partner co-development
- Evidence
- Company's own claim
Sources
Source summaries
Arla executives described joint development with an IT supplier and deployment across European markets. The company reported forecasts taking a few hours instead of days and 1.4% greater accuracy.
Full details are in the original sources.
