Project 01
Bank Customer Churn & Retention Analysis
Google BigQuery
SQL
Power BI
DAX
Data Validation
Business Question:
Which customer segments are most likely to churn, and how can
the bank prioritize retention efforts?
I analyzed 10,000 bank customer records using Google BigQuery and SQL for data validation, segmentation and exploratory analysis, then built an interactive Power BI dashboard with DAX measures to monitor churn KPIs and identify high-risk customer groups.
10,000
Total customers analyzed
20.37%
Overall churn rate
2,037
Churned customers
Key Findings
- Germany recorded the highest geographic churn rate at 32.44%.
- Inactive customers churned at 26.85%, compared with 14.27% among active members.
- Customers aged 51–60 had the highest age-group churn rate at 56.21%, while two-product customers had the lowest product-group churn at 7.58%.
Business Recommendations
- Investigate regional pricing, service quality, competitor offers and customer feedback in Germany.
- Prioritize re-engagement and retention campaigns for inactive customers and customers aged 41–60.
- Explore suitable cross-selling for one-product customers while monitoring the unusually high churn in small 3- and 4-product segments.