🚀 Customer Churn Prediction & Retention Analytics (SaaS)

🔗 Live Dashboard (Power BI):
https://bit.ly/3Qadvjk

---

📌 Business Problem

Customer churn is one of the biggest challenges in subscription-based (SaaS) businesses, directly impacting revenue and growth.

Companies need to identify high-risk customers early and understand the key drivers behind churn to improve retention strategies.

---

🎯 Objective

Develop an end-to-end analytics solution to:

• Identify customers at high risk of churn
• Understand the key factors influencing churn behavior
• Enable data-driven retention strategies
• Support product and business decision-making

---

🧠 Solution Overview

This project combines data analysis, machine learning, and business intelligence to transform raw customer data into actionable insights.

Key components:

• Exploratory data analysis to understand customer behavior
• Feature engineering to enhance predictive power
• Logistic Regression model to predict churn probability
• Interactive Power BI dashboard for business monitoring

---

🛠️ Tech Stack

• Python (Pandas, NumPy)
• Scikit-learn (Logistic Regression)
• Power BI (Data Visualization, DAX)
• SQL-style data modeling & segmentation

---

📂 Dataset

Telco Customer Churn Dataset (Kaggle)

---

🔍 Analytical Approach

1. Exploratory Data Analysis (EDA)

• Churn vs Non-Churn comparison
• Distribution analysis (Tenure, Monthly Charges)
• Correlation analysis
• Statistical testing (Chi-square)

2. Feature Engineering

• Revenue proxies (avg_revenue)
• Customer lifecycle segmentation (tenure_group)
• Categorical encoding

3. Machine Learning Model

• Model: Logistic Regression
• ROC-AUC: ~0.79
• Accuracy: ~75%

---

📊 Dashboard (Power BI)

This dashboard enables business teams to monitor churn risk and prioritize retention actions.

Key KPIs:

• Churn Rate
• Total Customers
• Total Churners
• % High-Risk Customers

Key Insights Visualized:

• Churn Rate by Contract Type
• Churn vs Monthly Charges
• Churn Trend by Tenure
• Customer Risk Segmentation

---

💡 Key Business Insights

• Contract Type: Month-to-month customers have significantly higher churn risk
• Customer Lifecycle: First 12 months are critical for retention
• Price Sensitivity: Higher monthly charges correlate with increased churn
• Risk Segmentation: Enables targeted retention campaigns

---

🎯 Business Impact

This solution demonstrates how data analytics can:

• Identify high-risk customers early
• Support targeted retention strategies
• Reduce potential revenue loss
• Improve product and pricing decisions

---

📈 Key Results

• Achieved ~0.79 ROC-AUC with Logistic Regression
• Identified key churn drivers (contract, tenure, pricing)
• Built ML-driven customer risk segmentation

---

📸 Dashboard Preview

---

🚀 How to Run

1. Clone repository
2. Install dependencies
3. Run notebooks
4. Open Power BI dashboard

---

✉️ Contact

• LinkedIn: https://www.linkedin.com/in/ruipc/
• GitHub: https://github.com/RuiCDev