{"name":"Customer Churn Prediction (demo)","dataset":"IBM Telco Customer Churn (Kaggle)","stack":["Python","scikit-learn","pandas","FastAPI"],"training":"Feature engineering (tenure groups, active services, TotalCharges); LogReg / Random Forest / Gradient Boosting; best model by ROC-AUC; F1-optimal binary threshold; full pipeline saved as joblib.","this_deploy":"Inference only — model file in model/churn_model.joblib","github":"https://github.com/vahdetkaratas/Customer-Churn-Prediction-System","notebooks_url":"https://github.com/vahdetkaratas/Customer-Churn-Prediction-System/tree/main/notebooks","docs":"/docs","test_metrics":{"model_name":"Gradient Boosting","roc_auc":0.8431,"f1":0.5935,"test_set":"Stratified 80/20 hold-out test set"}}