Churn Prediction Designer

Name: OpenModels
Creator: OpenModels
License: https://github.com/openmodelsrun/openmodels

AdvanceddataMinimum 32K context

Designs a customer churn prediction approach end to end: framing the target and prediction window, engineering behavioral and tenure features, choosing suitable models and evaluation metrics for imbalanced data, and planning how predictions feed retention actions. Focuses on leakage-free design and metrics that match the business goal.

churn machine-learning predictive-modeling feature-engineering retention

Use cases

Framing churn as a labeled prediction problem with a clear window
Designing leakage-free behavioral and tenure features
Choosing metrics for imbalanced churn data (PR-AUC, recall at k)
Planning how churn scores drive retention interventions

Example prompt

Help me design a churn prediction model for a B2B SaaS product.

Available data: subscription events, product usage logs, support tickets, and billing history.

Define the target and prediction window, propose features (and call out any that risk leakage),
recommend candidate models and evaluation metrics for the class imbalance, and outline how the
predictions should trigger retention actions.

Recommended models

claude-opus-5 gemini-3-6-flash gpt-5-5-pro

Compatible tools

claude-codecursorkiroany

Modalities

Input: text, code

→

Output: text, code

Author

OpenModels Community

@openmodelsrun