# How Early Is Early Enough? Design-Dependent Observation-Window Sufficiency in Subscription Churn Prediction

arXiv: https://arxiv.org/abs/2607.00473 · HTML: https://mlsanity.com/paper/2607.00473/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [An Integrated Transportation Distance Between Kernels and Approximate Dynamic Risk Evaluation in Markov Systems](https://mlsanity.com/paper/2311.06645/) (2023)
- [The Efficiency Frontier: A Unified Framework for Cost-Performance Optimization in LLM Context Management](https://mlsanity.com/paper/2605.23071/) (2026)
- [Rapid Prediction of Player Retention in Free-to-Play Mobile Games](https://mlsanity.com/paper/1607.03202/) (2016)
- [Behavioral Modeling for Churn Prediction: Early Indicators and Accurate Predictors of Custom Defection and Loyalty](https://mlsanity.com/paper/1512.06430/) (2015)
- [Early Churn Prediction from Large Scale User-Product Interaction Time Series](https://mlsanity.com/paper/2309.14390/) (2023)
- [Event history analysis with time-dependent covariates via landmarking supermodels and boosted trees](https://mlsanity.com/paper/2601.17605/) (2026)

## Built on by (most cited first, 8 of 8)

- [When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost](https://mlsanity.com/paper/2607.24010/) (2026)
- [Toward User-Conditioned Evaluation of Personal LLM Agents under Temporal Interventions](https://mlsanity.com/paper/2607.21635/) (2026)
- [From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs](https://mlsanity.com/paper/2608.04206/) (2026)
- [Explicit State Elicitation Is Not Enough: A Controlled Audit of Memory-Policy Classification](https://mlsanity.com/paper/2608.17247/) (2026)
- [Seasonal false alarms in customer churn and decline early-warning systems: adjacent-window labels confound seasonality with decline, and a year-over-year correction](https://mlsanity.com/paper/2608.18174/) (2026)
- [Noise Floor Audit for Agent Benchmarks](https://mlsanity.com/paper/2608.22331/) (2026)
- [GAUDI: Geometry-Aware Diffusion for Calibrated Air-Quality Time-Series Imputation](https://mlsanity.com/paper/2609.30340/) (2026)
- [What Breaks in Multi-Image Schema Application? Factorial Oracle Interventions Reveal an Instance-Information Bottleneck](https://mlsanity.com/paper/2610.19611/) (2026)

## Abstract (arXiv)

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 diminishing returns; descriptive inflection detectors place a knee between 30 and 120 days depending on the metric and model class. 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. A survival-filtered replication on educational-attrition data (OULAD) confirms the rising-curve shape in one behavior-dominated setting (floor ROC 0.56 vs. 0.88), though signal composition inverts.