DATA SCIENCE • BUSINESS INTELLIGENCE

E-Commerce Customer Retention Analysis

An end-to-end customer intelligence pipeline combining Python ETL, machine learning, relational data modeling, and Power BI to analyze retention and revenue risk.

Python MySQL Power BI DAX Machine Learning

01 — THE BUSINESS PROBLEM

Understanding customer retention and revenue risk.

Customer retention is a critical component of sustainable e-commerce growth. This project was designed to analyze customer behavior and identify patterns associated with churn and customer lifetime value.

The objective was to build a complete analytical pipeline rather than treating the dashboard as an isolated reporting layer.

02 — THE PIPELINE

From raw customer data to retention intelligence.

01

Python ETL

Prepared and transformed customer and transactional data for analysis.

02

MySQL

Organized analytical data using a relational star-schema architecture.

03

Churn Modeling

Applied machine-learning techniques to identify customer churn risk.

04

Power BI

Developed an executive dashboard using DAX-driven metrics.

03 — ANALYTICAL FOCUS

Connecting customer behavior with business value.

01

Customer Retention

Analyzed customer behavior to identify patterns associated with retention and potential churn.

02

Customer Lifetime Value

Built analytical measures to help understand the economic value of customers across the business.

03

Revenue Attrition

Connected customer-level retention analysis with the broader impact of lost revenue.

04 — TECHNOLOGY

The technical stack.

Python Python ETL Machine Learning MySQL Star Schema Power BI DAX

EXPLORE THE IMPLEMENTATION

View the source project.

View GitHub Repository →