Customer Journey (CJ)

“Informed and responsible analytics to understand and improve the customer journey”


Customers interact with an organization and its products and services in various ways: online shopping, after-sales, added services, social media, complaints, actual product usage (internet of things), upgrades, etc. To understand and to improve the overall customer journey, it is vital to link the different touch-points.  This is an extremely challenging multidisciplinary problem that we analyze from several complementary research perspectives: predictive analytics, customer journey mining, HCI, user psychology, marketing and innovation.

In interaction with an organization, customers leave many traces of their behavior. Being able to ‘read’ and interpret these traces, and being able to translate them to actionable knowledge requires expertise of data collection and statistical techniques, as well as an understanding of customers and the way in which they behave, collect information, and decide. There is a vast amount of data out there, but it needs the connection between data analytics, the user population, the artifacts that form an organization’s output, and knowledge about users and their interaction with these artefacts to find the stream of knowledge in a sea of data.


To do informed and responsible analytics to understand and improve the customer journey.

Research challenges

  • Gaining actionable and trustable insights extracted from data and guided by user theories. This calls for transparent, user interpretable and trustworthy models and model output.
  • Evaluation of the user experience and user-based validation of models induced from data and guided by user theories.
  • Conducting accountable, privacy-aware and ethics-aware analytics.

Project examples

  • NWO RATE-Analytics Rabobank, Achmea, TiU
    visual analytics, deep learning, NLP
  • KYC-Analytics Rabobank
    deep learning, NLP, pattern mining
  • STW CAPA Adversitement, StudyPortals
    context-awareness and concept drift handling
  • DDVP Philips Research
    pattern-based process mining, model adaptation, coaching models, recommenders, user experience
  • H2020 SODA Philips
    secure data science: big data analytics and multi-party computation
  • Interpolis
    Modeling prevention behavior