Problem: Identifying different customer groups was difficult when looking at large spreadsheets manually.

Work: Cleaned the data and used DBSCAN to group customers based on how much and how often they spend.

Tools: Python, Pandas, Scikit-learn, Matplotlib

Outcome: Visualized clear segments, making it easier to see different customer spending habits.

Problem: Sales numbers in the system sometimes didn't match up with the branch transaction records.

Work: Used SQL and Excel to build checks that find mismatches and automate the monthly reporting process.

Tools: SQL, Excel, Power BI

Outcome: Helped identify errors faster and ensured more accurate data for financial reports.

Problem: Monthly sales reports were slow to prepare and hard to visualize across different regions.

Work: Cleaned raw data and built a Power BI dashboard to track weekly sales trends and best-selling categories.

Tools: Power BI, Excel

Outcome: Reduced the time needed to prepare reports and made it easier to see how each category is performing.

Note: Work performed during internship at DataVerse Africa.

Problem: Exploring how local air quality changes correlate with public respiratory health complaints.

Work: Merged air quality records with public health numbers and plotted the results to find trends.

Tools: Python, Pandas, Matplotlib, Seaborn

Outcome: Visualized clear patterns between pollution spikes and hospital visits in specific zones.