arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.07047cs.LG
收藏

一种面向利润驱动型客户流失预防的预测-优化方法

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

University of Seville(塞维利亚大学);Instituto de Matemáticas de la Universidad de Sevilla (IMUS)(塞维利亚大学数学研究所(IMUS));University of Chile(智利大学);Instituto Sistemas Complejos de Ingeniería (ISCI)(工程复杂系统研究所(ISCI));Universidad de los Andes, Chile(智利安第斯大学)

Nuria Gómez-Vargas, Sebastián Maldonado, Carla Vairetti

AI总结:

针对传统利润驱动客户流失预防策略因用平均客户终身价值导致信息损失的问题,提出将客户定向任务构建为遗憾最小化问题的预测-优化方法,可通过随机梯度下降高效求解,在12个数据集上平均利润表现优于现有成熟策略。

摘要:

本文提出了一种用于利润驱动型客户流失预防的新型预测-优化方法。我们将留存活动的客户定向任务构建为一个遗憾最小化问题,核心目标是利用个体客户终身价值(CLVs)确保仅针对最具价值的客户开展活动。相比之下,许多利润驱动策略在关注流失概率的同时仅考虑平均CLV,这种数据聚合方式往往会导致显著的信息损失。我们提出的模型符合Predict-and-Optimize(PnO,预测-优化)框架的规范,可通过随机梯度下降方法高效求解。在12个客户流失预测数据集上的实验结果验证了该方法的有效性:就平均利润而言,其平均表现优于其他成熟策略。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑