PROJECT 02 / DATA / BUSINESS ANALYTICS
Customer Churn.
Find the story behind the exit.
From customer records to retention questions. An analytical workflow that makes patterns easier to explore and business decisions easier to discuss.
Look beyond the numbers.
01 / CONTEXT
The problem.
Customer data contains signals about retention, but raw records alone do not explain where to look. The analytical challenge is to organize those records into a consistent view that supports meaningful churn questions.
02 / APPROACH
From question to system.
Python and Pandas support data preparation, with SQL and SQLite used to explore customer records. Power BI brings the analysis into an interactive reporting layer supported by more than 20 DAX measures.
03 / ARCHITECTURE & WORKFLOW
How the pieces connect.
A conceptual overview of the project’s main components.
- 01Customer records
- 02Python / Pandas
- 03SQL / SQLite
- 04Power BI insights
04 / IMPLEMENTATION
Decisions that matter.
Separate preparation from presentation
A dedicated data preparation step makes the reporting workflow easier to inspect and repeat.
Make measures explicit
DAX measures give the dashboard a consistent analytical vocabulary rather than relying only on isolated chart values.
Keep interpretation grounded
The work explores retention and churn patterns; it does not claim a measured improvement in business retention.
05 / OUTCOMES & LEARNINGS
What the work taught me.
The analysis covers 3,000+ customer records and more than 20 DAX measures. A key lesson is to connect data preparation, query logic, and visual communication so that an insight can be traced back to the records behind it.
Built with.
Interface visuals are illustrative, not application screenshots. Explore the repository for source code and the current implementation.
NEXT CONNECTION / 03