The evaluation of the relationship with the customer and related benefits has become a key point for a company’s competitive advantage. Consequently, interest in key concepts, such as customer lifetime value and churn has increased over the years. However, the complexity of building, interpreting and applying customer lifetime value and churn models, creates obstacles for their implementation by companies. A proposed qualitative study demonstrates how companies implement and evaluate the importance of these key concepts, including the use of data mining and domain knowledge, emphasising and justifying the need of more interpretable and acceptable models. Supporting the idea of generating acceptable models, one of the main contributions of this research is to show how domain knowledge can be integrated as part of the data mining process when predicting churn and customer lifetime value. This is done through, firstly, the evaluation of signs in regression models and secondly, the analysis of rules’ monotonicity in decision tables. Decision tables are used for contrasting extracted knowledge, in this case from a decision tree model. An algorithm is presented, which allows verification of whether the knowledge contained in a decision table is in accordance with domain knowledge. In the case of churn, both approaches are applied to two telecom data sets, in order to empirically demonstrate how domain knowledge can facilitate the interpretability of results. In the case of customer lifetime value, both approaches are applied to a catalogue company data set, also demonstrating the interpretability of results provided by the domain knowledge application. Finally, a backtesting framework is proposed for churn evaluation, enabling the validation and monitoring process for the generated churn models.