2018 Finalist

Automated retention using churn modelling

De Persgroep Publishing

Asse, Belgium

Category Data and Research

Media associated with this campaign

Overview of this campaign

Data science can never be the main objective of a media company. It is a means to achieve business objectives. As such data science should not reside in a silo, but should understand both business and business people. This understanding can lead to great results.

In this campaign the goal was to leverage the insights provided by the churn model developed by Data Scientist in retention campaigns in order to reduce churn. This campaign had multiple sub-objectives:

  1. Present results of churn model to marketeers to engage them and get them enthousiastic
  2. Apply insights in an automated way to decrease churn
  3. Provide insights back to Marketing to show impact of this joint effort.

Results for this campaign

In this campaign we divided the entire customer base in deciles. Every decile determined the probability of churn for that customer. This analysis resulted in two main outcomes.

  1. In our contact center an indicator was implemented which showed the probability of churn for the customer who was currently on the phone. This allowed the operator to make a personalized offer when these people contacted us.
  2. We used the decile information in an automated retention campaign which launched in June 2017.  The average churn decreased by 18.6% in the period from June untill December. Next to a significant decrease in churn, an increase in ARPU of 2.03% was achieved by proposing personalized offers.


To contact a company representative about this campaign, click here for the INMA Member Directory

By continuing to browse or by clicking “ACCEPT,” you agree to the storing of cookies on your device to enhance your site experience. To learn more about how we use cookies, please see our privacy policy.