junfengn-ctrl/uplift-modeling-customer-retention
End-to-end uplift modeling pipeline for customer retention using T-Learner and X-Learner with XGBoost. Includes AUUC/Qini evaluation, SHAP interpretability, and business profit optimization.
This project helps customer retention and marketing managers identify which customers are most likely to respond positively to retention offers, such as discounts. It takes customer data (like contract type or tenure) and a history of past offers to predict who will stay only if given an incentive, leading to optimized offer strategies. The output helps decide which customers to target with retention campaigns to maximize profit and save resources.
Use this if you need to precisely target customers who are 'persuadable' by an offer and avoid spending marketing budget on those who will stay anyway or leave regardless.
Not ideal if your primary goal is simply to predict which customers will churn without considering the impact of specific interventions or offers.
Stars
65
Forks
9
Language
Python
License
MIT
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/junfengn-ctrl/uplift-modeling-customer-retention"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
retentioneering/retentioneering-tools
Retentioneering: product analytics, data-driven CJM optimization, marketing analytics, web...
iterative/demo-bank-customer-churn
Demo DVC project training a classification model on tabular data
Pradnya1208/Telecom-Customer-Churn-prediction
Customers in the telecom industry can choose from a variety of service providers and actively...
gattsu001/Telecom-Churn-Predictor
Predicts which telecom customers are likely to churn with 95% accuracy using engineered features...
Vegapunk-debug/customer-churn-agentic-retention-system
An end-to-end Machine Learning and Agentic AI system to predict customer churn and generate...