Beiersdorf – Consumer Packaged Goods
Sales forecasting for
smarter planning
“We aim to forecast sales accurately to enable better planning and allocation of resources.”
THE CHALLENGE
Beiersdorf’s emerging markets team lacked the ability to forecast future sales and market trends across 15 markets and over 80 market segments.
Although they received regular panel data, the process was entirely manual and reactive, with no integration of macroeconomic indicators or machine learning capabilities. This made resource planning difficult, inconsistent and disconnected from evolving market conditions
DISCIPLINES
Machine Learning, Cloud Architecture, Data Management, Process Automation
OUR APPROACH
Forecasting for
better planning
Uptimal proposed building a forecasting model using Beiersdorf’s monthly panel data, enriched with macroeconomic indicators to improve accuracy and context across emerging markets.
The model was designed to automatically ingest new data every month, generate updated forecasts and surface insights via dynamic dashboards, giving teams a scalable and data-driven way to plan ahead. Due to the combination of multiple countries and category units, a single model wasn’t suitable for all cases, so we developed a system that dynamically applied the best-fitting model for each specific market-category combination.
-
Data Exploration
We analyzed 36 months of historical panel data across multiple countries and categories, identifying patterns, seasonality and external drivers. Macroeconomic indicators were integrated to enrich the dataset and provide broader market context. -
Model Development
We developed a flexible forecasting system using Vertex AI on top of GCP, dynamically applying the most suitable model to each market-category combination. This ensured accuracy and scalability across Beiersdorf’s diverse portfolio. -
Data Visualization
We built interactive dashboards in Power BI to display both actual and forecasted sales. These visual tools empowered stakeholders to plan proactively, compare performance across markets and make data-driven decisions with confidence.
“Our work with complex market data
enabled us to design a forecasting
system that adapts to each case,
combining machine learning with
automation to ensure accuracy
and long-term scalability.”
Senior Data Scientist
RESULTS
Goals accomplished!
The final solution empowered Beiersdorf with automated forecasting and clear insights by transforming planning into a data-driven and scalable process.
-90%
reduction in manual effort required for monthly sales reporting
+87%
increase in forecasting accuracy across key market-category pairs
100%
automation of monthly forecast updates with new panel and macro data
reduction in manual effort required for monthly sales reporting
increase in forecasting accuracy across key market-category pairs
automation of monthly forecast updates with new panel and macro data
Get in touch
Questions? A project in mind? Talk to us.
- Analytics, tracking or data questions: real humans answer, fast
- Enterprise: audits, sGTM, GA4 360, BigQuery and MMM engagements
- Tell us your stack and goals, we reply within one business day