1. Business Problem
A retail banking institution experienced an unexpected 15% increase in customer account attrition across major geographic branches. Executive risk officers needed an interactive Power BI dashboard to analyze customer demographics, account balance distributions, credit score bands, and high-risk churn indicators to deploy targeted retention programs.
2. Project Objectives
- Develop a Power BI dashboard tracking customer churn rate, total bank deposits, and credit risk distributions.
- Calculate complex DAX measures for Churn Rate %, Average Account Balance, and Active Member Ratio.
- Design interactive slicers for Country, Gender, Age Group, and Credit Score Brackets.
3. Dataset Information
Banking customer transactions dataset covering 10,000+ customer profiles:
- Customer Profile: Customer ID, Surname, Credit Score, Geography, Gender, Age, Tenure (Years).
- Account Financials: Balance ($), NumOfProducts, HasCrCard, IsActiveMember, EstimatedSalary, Exited (1=Churned, 0=Retained).
4. Tools Used
Power BI Desktop
Advanced DAX
Power Query M Engine
Banking & Risk
5. Data Cleaning & Transformation
Transformation steps executed in Power Query & DAX:
1. Binned customer ages into custom generational age brackets (18-30, 31-45, 46-60, 60+).
2. Segmented credit scores into Risk Tiers (Poor, Fair, Good, Excellent).
3. Formulated DAX Measure for Customer Churn Rate:
Churn Rate % = DIVIDE(COUNTROWS(FILTER(Fact_Bank, Fact_Bank[Exited] = 1)), COUNTROWS(Fact_Bank), 0)
6. Key Performance Indicators (KPIs)
10,000
Total Bank Customers
20.37%
Customer Churn Rate
$76.48K
Average Account Balance
7. Dashboard Interface Showcase
8. Strategic Banking Insights
Finding 1: Germany & Inactive Member High-Risk Segment
Customers located in Germany exhibited a 32.4% churn rate — double that of France (16.1%). Inactive account holders aged 45–60 were 2.8x more likely to close their accounts.
9. Strategic Recommendations
- Deploy re-engagement incentives for inactive account holders holding single bank products.
- Review German regional banking fees and customer service response times to improve retention.
10. Technical Challenges
Balancing multiple binary flags (Active Member, Credit Card Holder, Churned) into a clean Star Schema data model was achieved using DAX dynamic measure switching.
11. Lessons Learned
Interactive demographic slicers combined with churn heatmaps empower banking executives to deploy targeted, region-specific customer loyalty campaigns.
12. GitHub Repository
Open Source Power BI Banking Templates
Inspect DAX measures and data model configuration on GitHub.
13. Downloads & Resources
14. Related Analytics Case Studies
