Enriching Customer Journey Prediction in KPN with Context Data

The customer journey approach is quickly becoming the game changer within KPN to become a customer-centric service provider and to improve the customer experience to an un-telco like level. Within this context, we have already connected various touch points of the customer, including calls, chats, store visits, online visits and engineer visits, and we are continuously adding more touch points to our customer journey dataset. In addition to these touch points also metadata, such as cost, is added to the data set, see figure below. For research purposes, we use only data from customers who have given permission for this.

We are starting to harvest the benefits from a customer journey approach. For example, we use insights about follow-up touch points to direct our efforts to improve the business process towards a more efficient and self-service oriented user portal. With these improvements in mind, we are now ready for the next step, with the following questions. Can we predict, given the contact history and the context such as demographic and performance data, what the next touch point(s) will be? If this is possible, how early can we get this prediction?

The final prediction model should be good enough to pro-actively help the customer in its journey towards a satisfactory solution. First, this will reduce customer effort and boost customer satisfaction. Second, this will allow us to be more efficient by combining touch points and optimize planning. The effectiveness of the prediction approach will be tested in a real customer satisfactory setting.

KPN is one of the largest Dutch telecommunication companies with a market share of approximately 40% for fixed services, with a customer base of about 3 million broadband customers and 5,5 million postpaid mobile customers. We deliver our services through several channels with a myriad of touchpoints.


For more information, contact dr. ing. Marwan Hassani.

Leave a Reply