Telco customer churn prediction

Built an end-to-end machine learning pipeline to predict customer churn in the telecom domain using data preprocessing, feature engineering, class imbalance handling, and model evaluation. Cleaned and transformed customer data, handled missing values and duplicates, encoded categorical variables, and engineered new behavioral features. Applied SMOTE on training data, feature scaling, and recall-focused hyperparameter tuning using GridSearchCV. Trained and evaluated multiple classification models, optimized decision thresholds, and analyzed churn-related patterns to identify high-risk customers and support retention decisions. Achieved strong churn detection performance with recall-driven model selection.