Time-sensitive Customer Churn Prediction based on PU Learning
This addresses customer retention for Internet companies, but it is incremental as it applies an existing PU learning technique to a time-sensitive scenario.
The paper tackles customer churn prediction by proposing a Time-sensitive Customer Churn Prediction (TCCP) framework using PU learning, which outperforms rule-based and traditional supervised models on real Alipay data.
With the fast development of Internet companies throughout the world, customer churn has become a serious concern. To better help the companies retain their customers, it is important to build a customer churn prediction model to identify the customers who are most likely to churn ahead of time. In this paper, we propose a Time-sensitive Customer Churn Prediction (TCCP) framework based on Positive and Unlabeled (PU) learning technique. Specifically, we obtain the recent data by shortening the observation period, and start to train model as long as enough positive samples are collected, ignoring the absence of the negative examples. We conduct thoroughly experiments on real industry data from Alipay.com. The experimental results demonstrate that TCCP outperforms the rule-based models and the traditional supervised learning models.