I clean, model and visualise data with SQL, Python, R, Excel and Power BI, and I’ve put it to work in telecom, banking and agriculture: growing revenue, spotting risk early, and forecasting harvests.
Cleaning, transforming and charting data until the pattern is obvious to anyone in the room.
Dashboards and reporting that teams open every week and check for themselves.
Models that forecast demand, segment customers and flag risk before it becomes a cost.
Turning analysis into a clear recommendation, a business case or a one-page brief.
Clustering 100,000 bank customers into six risk profiles, plus a short list of outliers that need a manual review.
Finding the subscribers most likely to upgrade, then reaching them by call, by SMS, or the moment they walked into 4G coverage.
Replacing a three-day manual reporting cycle with dashboards that marketing and executives can check for themselves.
A Power BI dashboard that brings soil, weather and yield forecasts together for Ghanaian farmers and the people who support them.
Yield models that gave farmers plot-level advice and contributed to an estimated 15% bigger harvest on pilot farms.
Linking churn to competitor activity and price changes, then turning the findings into one-page recommendations.
| Churn drivers | |
| Price moves | |
| Engagement |
Analysis that changes a decision rarely wins on the maths. It wins on the story: start from the decision, one number per sentence, and the why one click away.