研究订阅流失预测中早期行为数据的最佳观察窗口，发现效果依赖于具体设计。
How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction
- 通过多窗口分析发现45-90天为关键观察期，之后收益递减。
- 在手动续订群体中，120天内预测性能提升0.10（PR）。
- 结果受队列构建、目标定义和特征集影响，需明确说明实验条件。
订阅流失预测中，早期行为需要观察多久才足够？在公开的KKBox数据集上，通常以合同状态作为流失指标；但在手动续订的高流失群体中，早期行为显著提升了预测能力（120天时PR提升0.10）。九窗口充分性曲线显示，45-90天区间存在收益递减拐点。然而，在三种队列/任务设计下的压力测试表明，该曲线具有高度设计依赖性：例如在移动目标设定下，曲线反转且随特征集变化而漂移。因此，任何关于观察窗口充分性的结论都必须明确说明队列构造方式、目标定义和特征类型。所有证据来自单一音乐流媒体数据集，机制可能具有一般性，但数值结果未必可推广。
原文摘要 · Abstract (English)
How many days of early behavior suffice for subscription churn prediction? In the public KKBox dataset, the early indicator of churn is typically an indicator of someone's contract status; however, when looking in the heavily churned manual-renewal segment, having access to early behavior creates a substantial increase in prediction for that specific segment (PR +0.10 at 120 days). A nine-window sufficiency curve shows a diminishing-returns knee in a 45-90 day band. However, stress-testing over three cohort/task designs shows that this curve is singular to the design being tested; for example, in our test with a moving target, the curve inverts and can shift depending on the feature set used. Therefore, any window-sufficiency claim should state its cohort construction, target definition, and feature families. All evidence is from one music-streaming dataset; the mechanism should generalize but the magnitudes may not.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。