CASE STUDY
How did Danone, Nutricia and Żywiec Zdrój increase the accuracy of their demand forecasts to 97%?
About the project
Danone Poland successfully completed a comprehensive nine-month project to enhance demand planning processes across three key business units: Danone, Nutricia, and Żywiec Zdrój. The project aimed to integrate and optimize planning operations for a wide range of products—including dairy, specialized nutrition, and bottled water—distributed via 17 warehouses and covering a portfolio of over 9,000 unique SKUs.
This ambitious initiative focused on leveraging advanced technologies and collaborative strategies to significantly improve planning accuracy and efficiency.
Project Goals and Challenges
Data Integration and Management
A major challenge was managing a broad range of dispersed data sources, including marketing, sales, and weather data. Integrating and analyzing this data effectively was essential for improving demand planning.
Forecast Accuracy
The existing statistical models were not sufficient to deliver the level of forecast precision needed. Inaccuracies led to excess inventory or stockouts, reducing operational efficiency.
Advanced Technology Adoption
Implementing machine learning algorithms was a key objective, requiring robust data analysis and seamless system integration to improve forecast performance.
Collaborative Planning Approach
The shift toward consensus-based planning was critical for fostering cross-functional collaboration and aligning planning decisions with the company’s strategic goals.
Key Outcomes
Up to 97% Forecast Accuracy
By integrating sales and weather data with machine learning, the project achieved up to 97% forecast accuracy for key product groups, significantly enhancing reliability.
Optimized Inventory Levels
Improved forecasting led to better inventory control—reducing waste and inefficiencies and contributing to more sustainable operations.
Improved Inventory Turnover
The initiative resulted in a more accurate match between supply and demand, improving inventory turnover and enabling more data-driven decision-making.
Stronger Collaboration Across Teams
Consensus-based planning promoted a more collaborative and effective planning process, aligning departments around common goals.
Rigorous Testing and Hypercare Support
The project went through extensive unit, integration, and UAT testing. In the go-live phase, hypercare support ensured early issue resolution and stability.
Summary
Danone Poland’s demand planning transformation project—driven by SAP IBP, machine learning integration, and a collaborative planning methodology—successfully enhanced forecast accuracy, reduced inefficiencies, and fostered a culture of data-driven collaboration. The initiative serves as a strong example of how aligning technology, data, and people can elevate supply chain planning performance.
Any questions?
Let’s talk!
Luke Krukowski
Interested in this case study?
Let’s talk about your SAP IBP implementation