A predict-and-optimize approach to profit-driven churn prevention

TL;DR

This paper presents a new predict-and-optimize method for profit-driven customer churn prevention, focusing on targeting high-value customers to maximize profit, and demonstrates its effectiveness across multiple datasets.

Contribution

The paper introduces a novel predict-and-optimize framework that directly incorporates customer lifetime value into churn prevention strategies, improving profit outcomes.

Findings

Outperforms existing strategies in average profit across 12 datasets

Efficiently solvable with stochastic gradient descent

Aligns with predict-and-optimize principles for customer retention

Abstract

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.