Insights into market dynamics for a stronger competitive position
FrieslandCampina
- Customer case
- Data consultancy
- Data Analytics
- Data Science
- Analytics Engineering
FrieslandCampina Global facilitates local teams in Europe, Asia, and Africa. They want to gain a better understanding of the market and provide the teams with new insights. The goals are to strengthen their competitive position and to identify new opportunities for expansion.
FrieslandCampina asked us to contribute to their project by mapping market trends in terms of price, promotion and media.
- Price elasticity insights: How strongly did consumers react to price changes?
- Effects of promotions: Were promotions effective in attracting new customers or did they primarily lead to existing customers purchasing more?
- Media spending: Was media effectively utilized?
Approach
We employed marketing mix modeling based on linear regression. Our approach involved the following steps:
- Data preparation: Consolidating various data sources with different structures. We utilized data from FrieslandCampina Global, data from local teams, and public data. This included market information from sources such as Point of Sale data, product distribution, media spending, the impact of the COVID-19 pandemic, temperature, inflation rates, seasonality, and holidays. We consolidated this data from the cloud-based data warehouse, locally stored offline data, and online data sources.
- Data linking: We linked and transformed all data using the analytics engineering tool Dataiku. SQL was used to query the central database. The result was a dataset that provided a table view of all variables on a weekly or monthly basis.
- Clustering: We employed clustering to identify product groups based on sales patterns that potentially compete with each other, making them particularly interesting for the models.
- Variable testing: We examined the influence of all variables using linear regression with Python code. This allowed us to assess the impact relevant variables had on sales in previous years. We presented this information for each product, showcasing the drivers behind sales over time.
Throughout the entire data processing process, we maintained ongoing communication with the local teams. We enriched the insights from the data with their local knowledge and verified whether the assumptions they made based on their market expertise were accurate. This interaction contributed to creating buy-in for decision-making based on data-driven insights.
Results
The analysis served as a starting point for enabling local teams to work in a more data-driven manner. The methodology we established is scalable. With this knowledge, local teams can also analyze other product categories.
Through our knowledge transfer to the local teams, we are laying the foundation for them to take action independently. By involving them in the analysis and discussing the insights, they are increasingly contributing their own ideas and identifying new opportunities.
Together, we are making data more accessible, reliable, and insightful. There is now a single source of truth, and quality checks have been implemented. Data quality continues to improve, and the decision-making process within FrieslandCampina is becoming increasingly data-driven.
Want to know more?
Joachim will be happy to talk to you about what we can do for you and your organisation as a data partner.
Business Manager+31(0)20 308 43 90+31(0)6 23 59 83 71joachim.vanbiemen@digital-power.com
Receive data insights, use cases and behind-the-scenes peeks once a month?
Sign up for our email list and stay 'up to data':
You might find this interesting too
Unlocking the power of Analytics Engineering
The world of data is continuously shifting and so are its corresponding jobs and responsibilities within data teams. With this, an up-and-coming role appeared on the horizon: the Analytics Engineer.
Central data storage with a new data infrastructure
Dedimo is a collaboration of five mental healthcare initiatives. In order to continuously enhance the quality of their care, they organize internal processes more efficiently. Therefore, they use perceptions from the data that is internally available. Previously, they acquired the data themselves from different source systems with ad hoc scripts. They requested our help to make this process more robust, efficient and to further professionalise it. They asked us to facilitate the central storage of their data, located in a cloud data warehouse. The goal was to set up the data infrastructure within this environment, since they were already used to working with Google Cloud Platform (GCP).
Your Data Engineering partner
Generate reliable and meaningful insights from a solid, secure and scalable infrastructure. Our team of 25+ Data Engineers is ready to implement, maintain and optimise your data products and infrastructure end-to-end.
A scalable machine-learning platform for predicting billboard impressions
The Neuron provides a programmatic bidding platform to plan, buy and manage digital Out-Of-Home ads in real-time. They asked us to predict the number of expected impressions for digital advertising on billboards in a scalable and efficient way.
