Postpaid churn, contract, and ARPU analytics
A connected set of retention analytics for postpaid — contract-locking analysis, churn tracking, telesales next-best-offer targeting, and ARPU outlier detection.
- Role
- Lead analyst
- Where
- stc Bahrain
Some specifics are anonymised to respect commercially sensitive information.
Context
Postpaid is where customer value concentrates and where churn hurts most. The retention effort needed better inputs: which customers were out of contract, who was at risk, who to call, and where revenue was quietly leaking.
Problem
These questions were being answered inconsistently, in different tools, with different definitions of “at risk” and “out of contract”. Telesales was working lists that were not well targeted, and ARPU anomalies were only noticed after the fact.
What I did
I built a connected set of analyses: a contract-locking view showing who was in and out of commitment and when that changed; churn tracking with one consistent risk definition; a next-best-offer targeting feed for telesales; and an ARPU outlier detector using an IQR-based rule in DAX to flag accounts drifting away from their expected revenue. All of it surfaced in Power BI on a regular cadence.
Result
Telesales worked targeted lists instead of broad ones, retention had a single definition of risk, and ARPU outliers were caught while they could still be acted on.
What I learned
Most of the gain came from agreeing definitions once and reusing them everywhere. The IQR rule was deliberately simple so anyone could explain why an account had been flagged.