Consumer360 – Customer Segmentation & Churn Analysis

An end-to-end retail analytics solution that analyzes customer behavior, segments customers using RFM analysis, and identifies churn risks through an integrated pipeline of SQL, Python, and Power BI.

Customer Segmentation (RFM Analysis) Churn Analysis Customer Lifetime Value (CLV) SQL Data Processing ETL Pipeline Development Data Visualization (Power BI) Business Intelligence & Analytics
Dashboard Main View
Customer Overview A holistic view of customer demographics and overall behavior.
Retail Analysis View
Churn Analysis Detailed insights into customer retention and churn risk factors.

🎥 Video Walkthrough

Video Coming Soon

The detailed video walkthrough for this project is currently in production.

📌 Problem Statement

Retail businesses often lack visibility into customer behavior, making it difficult to identify high-value customers and detect early signs of churn.

Key challenges include:

  • Inability to identify profitable customer segments
  • Lack of insights into customer engagement and retention
  • Difficulty in designing targeted marketing strategies
  • Absence of a unified Customer 360° analytical view

This project addresses: How can businesses segment customers effectively and proactively reduce churn using data-driven insights?

⚙️ Approach & Methodology

  • Extracted and cleaned retail data using SQL
  • Performed data aggregation and transformation for analysis
  • Conducted RFM (Recency, Frequency, Monetary) analysis using Python
  • Calculated Customer Lifetime Value (CLV) for segment evaluation
  • Segmented customers into: Champions, Loyal Customers, At Risk, Low Engagement
  • Built automated ETL pipeline for data processing and refresh
  • Developed interactive Power BI dashboards for business insights

🧠 Concepts & Skills Applied

RFM Analysis
SQL Processing
Power BI
ETL Pipeline

📊 Key Insights

  • Champion customers contribute the highest revenue and CLV
  • At-Risk customers show declining engagement and higher recency values
  • West and South regions generate the highest sales
  • Electronics and Clothing dominate total revenue contribution
  • A small percentage of customers contribute a large portion of revenue (Pareto Principle)
  • Loyal customers provide stable and recurring revenue
  • Low-engagement customers indicate untapped growth opportunities

📈 Dashboard Highlights

⭐ Retail Performance Dashboard

  • Total Sales, Orders, Customers, Quantity
  • Monthly Sales Trends
  • Sales by Region & Country
  • Product & Category Performance

⭐ Customer Segmentation Dashboard

  • RFM-based customer segmentation
  • CLV analysis
  • Churn Risk vs Active Customers
  • Segment-wise contribution and behavior

💼 Business Recommendations & Impact

  • Launch targeted retention campaigns for At-Risk customers
  • Introduce loyalty programs for Champions and Loyal segments
  • Increase marketing investment in high-performing regions
  • Promote high-performing product categories strategically
  • Implement personalized product recommendations
  • Monitor churn-risk segments proactively

Expected Impact:
• Improved customer retention and reduced churn
• Increased revenue through targeted marketing
• Better customer segmentation and engagement strategies
• Enhanced decision-making using Customer 360° insights

⚡ Advanced Features

  • RFM-based segmentation for customer classification
  • Customer Lifetime Value (CLV) calculation
  • Automated ETL pipeline using Python & Task Scheduler
  • Multi-tool integration (SQL + Python + Power BI)
  • Real-world retail analytics workflow simulation
  • Dynamic Power BI dashboards for business decision-making
GITHUB REPOSITORY ← BACK TO ALL PROJECTS