Machine Learning Project
Predicting customer attrition to support proactive retention strategies
This project focuses on identifying customers at risk of churn using supervised machine learning models. It demonstrates end-to-end data science workflows, from feature engineering and model training to business interpretation and dashboarding.
🚧 Project Status
This project page is currently a placeholder. Detailed analysis, model results, and dashboards will be added soon.
Customer churn directly impacts revenue and growth. The goal is to predict which customers are likely to churn so that targeted retention strategies can be applied before loss occurs.
Historical customer data including demographics, usage behaviour, contract details, and service interactions.
Logistic Regression, Random Forest, and Gradient Boosting models evaluated using ROC-AUC and business-aligned metrics.
Model evaluation, feature importance analysis, and an executive-ready churn dashboard.