Enterprise-grade Telecom Customer Churn Prediction system blending advanced machine learning (XGBoost), real-time Flask API deployment, and interactive Streamlit dashboards to enable data-driven customer retention strategies.

this project focuses on predicting telecom customer churn using supervised machine learning models. by analyzing historical data such as contract type, internet service usage, and billing method, we aim to identify customers who are at risk of leaving the company.

This project leverages Python (Pandas, Prophet, Matplotlib) to track segment-wise performance, calculate kebele-level market penetration rates, and deliver a 12-month forecast. Provides actionable geographic and segment-specific insights for resource allocation and and strategic planning.

Random Forest Classifier for Customer Churn Prediction

This project uses real-world telecom customer data to predict churn behavior using machine learning. It includes data cleaning, exploratory data analysis (EDA), feature engineering, model training (Logistic Regression and Random Forest), and strategic business recommendations. The final model is ready for deployment in customer retention systems.

A full data analytics case study that identifies why telecom customers churn, predicts future churn with machine learning, and visualizes actionable business insights in Power BI dashboards.