While business-to-customer (B2C) companies, in the telecom sector for instance, have been making use of customer churn prediction for many years, churn prediction in the business-to-business (B2B) domain receives much less attention in existing literature. Nevertheless, B2B-specific characteristics, such as a lower number of customers with much higher transactional values, indicate the importance of identifying potentially churning customers. To achieve this, we implemented a prediction model for customer churn within a B2B software product and derived a model based on the results. For one, we present an approach that enables the mapping of customer- and end-user-data based on “customer phases” which allows the prediction model to take all critical influencing factors into consideration. In addition to that, we introduce a B2B customer churn prediction process based on the proposed data mapping.