{"ID":5551964,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T05:37:16.483855972Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00473","arxiv_id":"2607.00473","title":"How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2607.00473","url_pdf":"https://arxiv.org/pdf/2607.00473v1","authors":"[\"Xiao Han\",\"Yao Xiao\",\"Chenyu Wu\",\"Tongchen Zhang\"]","published":"2026-07-01T05:47:38Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false}