A predict-and-optimize approach to profit-driven churn prevention
This addresses the issue of inefficient retention campaigns in customer relationship management by reducing information loss from data aggregation, though it appears incremental as it builds on existing predict-and-optimize frameworks.
The paper tackles the problem of profit-driven churn prevention by introducing a predict-and-optimize method that targets customers based on individual lifetime values, achieving the best average performance on 12 datasets compared to other strategies.
In this paper, we introduce a novel predict-and-optimize method for profit-driven churn prevention. We frame the task of targeting customers for a retention campaign as a regret minimization problem. The main objective is to leverage individual customer lifetime values (CLVs) to ensure that only the most valuable customers are targeted. In contrast, many profit-driven strategies focus on churn probabilities while considering average CLVs. This often results in significant information loss due to data aggregation. Our proposed model aligns with the guidelines of Predict-and-Optimize (PnO) frameworks and can be efficiently solved using stochastic gradient descent methods. Results from 12 churn prediction datasets underscore the effectiveness of our approach, which achieves the best average performance compared to other well-established strategies in terms of average profit.