Project Overview

This project analyzes customer churn in a retail banking environment using SQL for data preparation and analysis, and Power BI for visualization. The goal is to identify churn drivers and deliver actionable insights into customer behavior across different demographics, financial tiers and product usage levels that support retention-focused decision-making.

Business Problem

Customer churn directly impacts revenue and long-term profitability in retail banking. Management observed increasing customer churn but lacked clarity on who is leaving, why they are leaving and which customer segments pose the highest financial risk. This project addresses those gaps through structured analysis and executive-level reporting.

Dataset & Tools

Dataset: Bank Customer Churn (Maven Analytics)

Tools Used:

• SQL (PostgreSQL) – data cleaning, feature engineering, KPI analysis
• Power BI – dashboarding and visualization
• Notion – business documentation
• GitHub – SQL scripts and project structure

Dataset Description

The analysis is based on a dataset of bank customers with the following key attributes:

• Demographics: Age, Gender and Country.
• Financial Profile: Credit Score, Balance and Estimated Salary.
• Engagement: Tenure, Number of Products, Credit Card ownership and Active Member status.
• Target Variable: Exited Indicating whether the customer churned.

Data Cleaning & Transformation (SQL)

The raw data underwent a rigorous cleaning process to ensure analytical integrity:

• Type Casting**:** Converted string-based numerical fields (CreditScore, Age, Balance, etc.) into appropriate integer and numeric types for calculation.