A machine learning project focused on predicting customer churn using classification techniques. The model leverages logistic regression and ensemble methods to achieve 85%+ accuracy, with XGBoost and feature engineering driving a ~12% improvement over the baseline. A full analytical report with visualizations was produced to support data-driven business decisions.
October 2025 – November 2025
XGBoost classifier combined with logistic regression, boosting prediction performance ~12% above the baseline model.
ROC-AUC scoring, confusion matrices, and precision/recall analysis used to validate and compare model performance.
Detailed report with key statistics, visualizations, and insights to support data-driven retention strategies.
Baseline Accuracy: ~73%
Final Accuracy: 85%+ (+12% via feature engineering & XGBoost)
Primary Metric: ROC-AUC
Key Features: Tenure, contract type, monthly charges, support calls
Output: Detailed report with charts & retention insights