Danone increases convenience channel sales by 10% across its network


Most consumer goods companies segment their distribution network to design trade marketing actions that work. However, normally the segmentations are based solely on billing data, failing to capture what occurs at the point of sale level. It’s impossible to answer questions such as: Which consumer profiles do you attract? What are the levels of footfall? In essence: Why do some products perform better than others?

Danone Dairy had been trying to make sense of its convenience channel for 70 years without any insightful results. What’s the winning product mix among the more than 200 SKUs of the brand? How can common consumption patterns be found amongst local supermarkets, neighbourhood stores and food?

Finally, in 2018 Favio Hernán Zarbano managed to organise the Danone Dairy network by designing three ideal store models that could be applied to different convenience store types. How did he do it? By enriching Danone’s sales data with data that described the surroundings of their points of sale. In just a few months, Favio was able to solve the 70-year-old problem.

What you will learn in this case study…

  • How Danone classified a chaotic network of 13,000 points of sale into three types of stores: urban, rural and impulse
  • What point of sale clustering analysis is and how it can be used to maximise sales across the network
  • How data that describes external market conditions can be combined with billing information and used to define product mixes
  • Other potential benefits clustering poses for other channels to reinforce any trade marketing strategy

Get your case study now!

Thank you! We will contact you soon.