Challenge: Jumboline was losing over a quarter of its customers annually, but leadership lacked visibility into who was leaving, why they were leaving, and where the revenue risk was concentrated.

Action: Built an end-to-end churn analysis across 7,043 customer records, using Python to clean and validate the data, PostgreSQL to structure the analysis, and Power BI to deliver a six-page interactive dashboard the retention team could use for ongoing monitoring.

Key Findings:

• Compounding Risk: Identified four warning signs that, when present together, were associated with a 71.16% churn rate.

• Revenue at Risk: Flagged 182 active customers showing all four risk factors and 782 showing three or more, together representing 19.18% of active monthly recurring revenue.

• Retention Opportunity: Customers with neither automatic payments nor protective add-ons churned at 40.4%, versus just 11.7% among those with both.

Business Impact:

• Early Warning: Gave the retention team a self-service workflow to identify high-risk customers before they churn.

• Targeted Retention: Enabled the team to prioritize outreach by risk pattern, focusing on the customers representing the greatest potential revenue loss.