🎓 Actuarial Science Background | Statistical Rigour Meets Business Impact
🌍 Open to Remote Opportunities | 🕐 GMT+3
I am a data analyst with an Actuarial Science foundation, combining mathematical precision with business storytelling. I specialise in transforming complex datasets into clear, actionable insights that drive strategic decisions.
Over the past months I have built a structured portfolio across Excel, SQL and Power BI — working on real datasets in banking, healthcare, retail and HR analytics. Every project is published on GitHub with full documentation and board-ready findings.
What sets me apart:
- 🧠 Actuarial background — advanced statistical thinking built in, not bolted on
- 📊 Business-first approach — I answer the question behind the question
- 🔁 End-to-end capability — from raw data to executive recommendation
- 🌍 International ambition — building skills and portfolio to work globally
| Spreadsheets | Database | Visualisation | Programming |
|---|---|---|---|
 |
 |
 |
 |
| Power Query • DAX • VBA | T-SQL • CTEs • Window Functions | Dashboards • DAX Measures • Drill Through | pandas • matplotlib |
Excel: Power Query, Power Pivot, DAX, VBA Macros, Dynamic Arrays, XLOOKUP, Statistical Analysis, Scenario Manager, Goal Seek, Dashboard Design
SQL: T-SQL, SELECT/WHERE/GROUP BY/HAVING, Aggregate Functions, INNER & LEFT JOINs, Subqueries, CTEs (multi-level), Window Functions (RANK, PARTITION BY, LAG, LEAD, Running Totals), CASE WHEN, Date Functions, String Functions, Primary & Foreign Keys, Views, Stored Procedures, Indexes, Data Quality Auditing
Power BI: SQL Server Connector, Import Mode, Power Query (M Language), Star Schema Modelling, DAX Measures, Calculated Columns, Drill Through, Bookmarks, Page Navigation, KPI Cards, Multi-page Dashboard Design
Interactive 3-page Power BI dashboard built on the Olist SQL analysis — full end-to-end pipeline
| Metric | Finding |
|---|---|
| Total Orders | 99,441 across 4 relational tables |
| Total Revenue | $16.01M across 27 Brazilian states |
| Top State | SP — $5.77M revenue | 8.7 day avg delivery |
| Credit Card Share | 78.34% of total revenue |
| Repeat Customer Rate | 0.00% — not a single repeat buyer |
| Avg Delivery | 12 days Brazil average | 97.02% delivered |
Key Features: Drill through from state chart to delivery detail page • Bookmarks reset button • Year slicer • Hidden drill through page • DAX measures validated against SQL queries
Power BI DAX Power Query SQL Server Connector Star Schema Drill Through Bookmarks M Language
🔗 Built on: Olist E-Commerce — SQL Analysis
Detecting 473 fraud cases among 283,726 real credit card transactions
| Metric | Finding |
|---|---|
| Fraud Rate | 0.1667% — 473 cases in 283,726 transactions |
| Fraud Avg Amount | $123.87 vs Legitimate $88.41 — 40% higher |
| Peak Fraud Hour | 2am — 1.4550% rate, nearly 10x average |
| Fraud in Normal Transactions | 93.9% — Z-Score alone misses 444 of 473 cases |
| Total Fraud Value | $58,591.39 across 473 transactions |
Key Recommendation: Multi-factor detection combining amount, time and behavioural signals — Z-Score alone is insufficient.
T-SQL Views Stored Procedures Indexes Z-Score Anomaly Detection ROW_NUMBER() PERCENTILE_CONT Data Cleaning Deduplication
Identifying the key drivers of employee attrition across 1,470 IBM records
| Metric | Finding |
|---|---|
| Overall Attrition Rate | 16.12% — 237 employees left |
| Highest Risk Department | Sales — 20.63% attrition rate |
| Income Gap | Leavers earned $2,045/month less than stayers |
| Highest Risk Age Group | Under 25 — 39.18% attrition rate |
| Highest Risk Role | Sales Representatives — 39.76% attrition | $2,626 avg income |
| Most Stable Role | Research Directors — 2.50% attrition | $16,033 avg income |
Key Recommendation: Compensation is the strongest predictor of retention across all 9 job roles. Revising Sales Representative pay is the single highest-return intervention available.
T-SQL CTEs Window Functions RANK() PARTITION BY Subqueries CASE WHEN GROUP BY CAST
Multi-table revenue, delivery and retention analysis across 99,441 orders
| Metric | Finding |
|---|---|
| Order Growth | 1 order (Sep 2016) → 7,289/month (Nov 2017) in 14 months |
| Credit Card Revenue Share | 78.34% — $163 avg order value |
| Delivery Performance | Only 31.82% arrive within 1 week — 12 day average |
| Top State | SP — $5.77M revenue, 8 day avg delivery |
| Repeat Customers | 0% — every customer purchased exactly once |
Key Recommendation: Zero repeat buyers is an existential retention risk — every customer acquired is lost after one purchase.
T-SQL Multi-table JOINs CTEs Window Functions Date Functions Primary Keys Foreign Keys Data Quality Auditing UNION ALL
🔗 Also available as: Power BI Dashboard — Interactive 3-page dashboard completing the full Data → SQL → Power BI pipeline
Multi-dimensional revenue analysis across time, geography and product categories
| Metric | Finding |
|---|---|
| Top Region | West — 31.4% of total revenue |
| Top State | California — 19.7% concentration risk |
| H1 2019 Forecast | $340,533 (FORECAST.ETS) |
| Growth Required for $1M Target | 77% |
Key Recommendation: California concentration represents portfolio risk — diversification into underperforming regions would reduce revenue volatility.
Power Query Power Pivot DAX VBA Macros FORECAST.ETS Scenario Manager Goal Seek Dynamic Arrays
Loan default risk analysis across a KES 12.28M banking portfolio
| Metric | Finding |
|---|---|
| Portfolio Value | KES 12,285,000 |
| Overall Default Rate | 20% |
| Highest Default Region | Nairobi — 60% of all defaults |
Key Recommendation: Nairobi concentration in both portfolio value and defaults signals a geographic risk — regional diversification and tighter Nairobi credit scoring criteria warranted.
Power Query XLOOKUP Pivot Tables Conditional Formatting KPI Dashboard
Patient admission, cost and risk analysis across 40,235 records
Advanced Excel Statistical Analysis Dashboard Design Data Cleaning
Actuarial Science — University education in statistical modelling, risk assessment and financial mathematics. This foundation gives my data analysis a level of mathematical rigour that goes beyond standard analyst training.
Self-directed Upskilling:
- ✅ Excel — Power Query, DAX, VBA, Statistical Analysis
- ✅ SQL — T-SQL, Window Functions, CTEs, Advanced Queries
- ✅ Power BI — Dashboards, DAX Measures, Drill Through, Bookmarks, SQL Server Connector
- 📅 Python — pandas, matplotlib, scikit-learn (Planned)
Junior to Mid-level Data Analyst roles — remote — where I can:
- ✅ Deliver business-ready analysis and dashboards
- ✅ Apply statistical expertise to real business problems
- ✅ Work with cross-functional teams in fast-paced environments
- ✅ Grow toward senior analyst and data science capability
Industries of interest: Financial Services, Banking, Consulting, Healthcare, Telecoms
