Understanding Consumer Behavior With Insights From Unilever and Capgemini

Scaling AI Marie Merveilleux du Vignaux

We are in the midst of a digital marketing revolution. Consumers are constantly changing: their journeys are more fragmented, their desires are shifting, and their preferences are drifting towards online purchases. Consumers are thus leaving massive digital footprints and organizations need to learn how to take advantage of these footprints to best serve customers in return.

In order to understand these digital consumers and better cater to their needs, organizations are looking for insights in the large amounts of data they are gathering using data science and analytics. During the just-released EGG On Air Episode, Jason Hardman, Head of PDC Lab at Unilever, and Jon Howells, Lead Data Scientist at Capgemini, discuss how organizations can use data and AI to better understand and respond to consumers.

→ Watch the Full Episode Now!

Grasping Consumer Voices Through People Data Centers

Unilever has 30 people data centers (PDC) around the world to service intelligent insights that drive the organization’s marketing decisions, product development, logistics, and strategies. The PDCs are structured in a hub and spoke operating model. Each PDC is composed of a centralized capability center, the PDC lab, and embedded teams present across the business, known as PDC squads.

  • The PDC lab helps supply the data by making sure it is coming in continuously and being ingested correctly. The lab is also in charge of building common services and capabilities that bring in new analytical tools to the arsenal.
  • The squads work closely with the business. Through them, Unilever has a close view of the business and can interact and receive questions delivering insights that help the organization grow and scale AI.

These PDCs help Unilever understand the voices of consumers notably by combining different data sources. The PDC exists to understand the consumers it serves and that understanding comes from a lot of data sources. To be able to engage with consumers across numerous channels and provide meaningful insights, organizations need to be able to tap into multiple sources. It is by combining first, second, and third-party data sources that Unilever manages to understand its consumers’ voices. Some examples of of data sources PDCs combine include data from:

  • Forums
  • Blogs
  • Social media
  • Customer support
  • Research

Each data source tells the organization something that adds to the total story of the consumer.

It’s only by combining all that data together that you get that holistic picture.”

Jason Hardman

Jason Hardman and Jon Howells on an Egg On Air Episode

Driving Insights From Social Media Using NLP

Jon Howells notes that strong advances in NLP are allowing companies to get more and better insights from these types of unstructured data through methods such as sentiment analysis, topic modeling, and text classification. Indeed, the global NLP market is expected to reach nearly $30 billion by 2025, as the approach is the bedrock for any sort of social analysis.

One example of how Unilever uses NLP is in its effort to understand and improve product quality. Unilever uses public statements and combines review data with core center data and social data through its Digital Voice of the Consumer (DVOC) service. DVOC aims to collect and use such data and make it accessible across the organization to improve products. NLP and other AI techniques are used on this data to bring product quality issues to the service. The quality team then discusses the findings and takes the necessary next steps to improve the quality of the product and customer satisfaction.

Conclusion

The final touch is embedding AI across the whole organization and making sure everything is used and beneficial. Thanks to its powerful and structured PDCs, Unilever has now reached that stage. The organization has a direct connection to the end business stakeholder as the PDCs are embedded in the whole business structure.

You May Also Like

A Sneak Peek of Season 5 of the Banana Data Podcast: Humanizing Data Science and AI

Read More

A Day in the Life of a Data Scientist at Pfizer

Read More

Understanding the Power of Data

Read More

Using Data Privacy to Introduce AI Regulation: The Canadian Bet

Read More