📉 Customer Churn Analysis & Retention Strategy

Predict churn. Retain customers. Drive growth.

---

🔍 Overview

A full-stack data science project built on a real-world telecom dataset to uncover the key drivers of customer churn and craft data-driven retention strategies. From raw data to business insights — this project covers it all.

📊 Predicts churn probability per customer · 🎯 Identifies at-risk segments · 💡 Recommends targeted retention actions

---

✨ Features

Feature	Description
🔬 Exploratory Analysis	Deep statistical insights with rich visualizations
🤖 Churn Prediction	ML model to score each customer's churn probability
📊 Interactive Dashboard	Streamlit-powered web dashboard for business users
💼 Business Reports	Auto-generated Excel & PowerPoint output files
🎯 Retention Strategies	Actionable, data-backed recommendations

---

🗂️ Project Structure

Customer_Churn_Analysis-Retention_Strategy/
│
├── 📄 analysis.py              # Core analysis & ML pipeline
├── 📊 dashboard.py             # Interactive Streamlit dashboard
├── 📋 requirements.txt         # Python dependencies
│
├── 📁 data/
│   └── WA_Fn-UseC_-Telco-Customer-Churn.csv
│
└── 📁 output/
    ├── 🖼️  *.png               # Visualization charts
    ├── 📈 churn_predictions.csv
    ├── 📊 churn_business_report.xlsx
    └── 📑 churn_presentation.pptx

---

🚀 Getting Started

1️⃣ Clone the Repository

git clone https://github.com/MM-Robin/Customer_Churn_Analysis-Retention_Strategy
cd Customer_Churn_Analysis-Retention_Strategy

2️⃣ Set Up a Virtual Environment

python -m venv venv
source venv/bin/activate       # Windows: venv\Scripts\activate

3️⃣ Install Dependencies

pip install -r requirements.txt

---

▶️ Usage

Run the Analysis

python analysis.py

Executes the full pipeline: data preprocessing → feature engineering → model training → output generation.

Launch the Dashboard

python dashboard.py

Opens an interactive web dashboard to explore churn patterns and model insights visually.

---

📦 Dependencies

Python 3.8+   pandas   numpy   scikit-learn
matplotlib    seaborn  plotly  streamlit

---

📂 Dataset

Uses the IBM Watson Analytics — Telco Customer Churn dataset, covering:

• 👤 Customer demographics
• 📡 Service usage patterns
• 💳 Billing & contract details
• ✅ Churn labels

---

📈 Results

The project delivers:

• ✅ Trained churn prediction model with accuracy metrics
• 📌 Top churn-driving factors identified
• 💡 Segment-specific retention recommendations
• 📊 Interactive visualizations & business-ready reports

---

🤝 Contributing

Contributions are welcome!

1. Fork the repository
2. Create a feature branch: git checkout -b feature/your-feature
3. Commit your changes: git commit -m "Add your feature"
4. Push and open a Pull Request

---

👤 Author

Mainuddin Monsur Robin

---

If you found this project useful, consider giving it a ⭐