Customer Churn & Profit Optimization (End-to-End ML)
تفاصيل العمل
Tools: Python, Scikit-learn, SHAP, Streamlit Developed a revenue-driven ML pipeline to address a 26.5% churn rate, targeting a potential $3.68M revenue loss. Optimized Model Recall & AUC to minimize "False Negatives," ensuring high-risk customers are identified before churning. Engineered a "Profit-Based Priority Score" (Prob × CLTV) to maximize retention ROI and optimize budget allocation.
مهارات العمل
بطاقة العمل
طلب عمل مماثل
