Time-sensitive Customer Churn Prediction based on PU Learning

TL;DR

This paper introduces a time-sensitive customer churn prediction framework using PU learning, which effectively predicts likely churners early by leveraging recent data and positive samples, outperforming traditional models.

Contribution

The novel TCCP framework applies PU learning to time-sensitive churn prediction, addressing the challenge of limited negative samples and improving early detection accuracy.

Findings

TCCP outperforms rule-based models.

TCCP surpasses traditional supervised models.

Effective early churn prediction on industry data.

Abstract

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.