Data Analyst specializing in Credit Risk, Product, and CRM Analytics — turning customer, credit-risk, and product data into decisions around default risk, churn, and growth opportunities, validated through statistical testing rather than assumption. Across eight analytical projects, I use SQL, Python, Excel, and Tableau to move from raw data and data-quality problems to business analysis, visualisation, and measurable recommendations.
📍 Ilorin, Nigeria (WAT, UTC+1) · Open to remote roles · Full-time or contract
- Data → Decisions: I identify business problems first, then use data to solve them — not the other way around
- End-to-End Delivery: SQL extraction → Python analysis → Excel/Tableau dashboards → executive-ready insights
- Quantified Impact: Every project uncovers measurable business value — default risk, revenue at risk, churn risk, or sales uplift
- Risk-Led Analysis: I investigate the business risks behind the data — from credit default and customer churn to product engagement gaps and revenue leakage
- Collaborative: I translate technical findings into plain business language for non-technical stakeholders
- Self-Directed: Self-taught analyst — built proficiency in SQL, Python, and Tableau independently, with a track record of learning new tools as projects demand
- Business-First: Every analysis starts with a business question, not the dataset
- Structured Thinker: Mathematics background shows up in how I frame problems — rigorous, methodical, evidence-based
- 8 end-to-end analytics projects — from SQL pipelines and Python ETL to Excel and Tableau dashboards
- Core focus: Credit risk, product analytics, and CRM/retention analytics
- Featured methodology: Bureau-independent credit risk segmentation using 149,999 borrower records
- DataCamp Certified Associate Data Analyst — Jul 2026
- Certified Data Analyst — TS Academy, 2026
- Forage simulations: Quantium + Deloitte + BCG
💳 Fintech Credit Risk Analysis — 55.0% default rate among borrowers with Critical behavioural and exposure risk · View
📉 Telco Customer Churn Analysis — £1.67M annualised revenue at risk uncovered via SQL + Excel · View
🛍️ E-Commerce Customer Retention & Revenue Stability Analysis — 21.27% average retention rate uncovered beneath 8× YoY revenue growth · View
📈 Quantium Retail Analytics — +33.5% sales uplift through trial-store analysis · View
🚚 Logistics Performance Analysis — –609% margin route surfaced across 85K+ trip records · View
🛒 Superstore Sales Exploration — 50.4% loss-order rate uncovered across 8,399 orders · View
SQL · MySQL · Python · Pandas · Risk Segmentation · Tableau
Built a bureau-independent credit risk segmentation pipeline using 149,999 borrower records. The project combined SQL-based data quality analysis, Python-derived behavioural risk scoring, and a custom Exposure Index to identify borrowers who may require differentiated credit-risk treatment when traditional bureau information is limited.
Key findings:
- Borrowers scoring Critical on both behavioural risk and exposure risk defaulted at 55.0%
- Borrowers with zero open credit lines defaulted at 25.64% — the highest rate among credit-line segments
- A data-quality placeholder flag showed a 54.65% default rate, outperforming every engineered feature and demonstrating the importance of data-quality analysis before modelling
- Missing income affected 19.82% of borrowers, requiring an explicit
Indeterminateexposure category rather than forced scoring - Built a bureau-independent risk segmentation methodology designed as a proof of concept for digital lending environments where traditional credit history may be limited
View Repository · Live Risk Check
SQL · MySQL · Microsoft Excel · Three-Pillar Framework (Customer · Revenue · Risk)
End-to-end churn analytics project built on MySQL and Excel — 22 SQL queries and 17 analysis-ready datasets feeding a four-dashboard executive reporting suite covering customer behaviour, revenue exposure, and structural business risk.
Key findings:
- 26.54% overall churn rate, placing £1.67M in annualised revenue at risk
- Month-to-month contracts churn at 42.71% — 15× the rate of two-year contracts
- Fiber optic customers drive 62.11% of revenue while recording the highest churn rate (41.89%)
- 814 high-risk customers identified pre-churn, churning at 69.53% — 3.3× the base rate
Microsoft Excel · Power Query · Pivot Tables · Dashboard
Analysed customer retention dynamics, revenue stability, and geographic concentration risk for a UK-based e-commerce retailer across a structured 10-phase Excel workflow.
Key findings:
- Revenue grew 8× YoY — but CV of 78.60% confirms high instability beneath the growth
- Average retention rate of 21.27% — growth was acquisition-driven, not loyalty-driven
- 84.42% of revenue concentrated in the UK — extreme single-market dependency
Python · Pandas · Statistical Matching · Forage Job Simulation
Cleaned and merged 264,836 transactions with 72,637 loyalty customer records to analyse chip category purchasing behaviour across customer segments. Built a correlation-based control store matching model to evaluate a new trial layout's commercial impact.
Key findings:
- Store 77 delivered the strongest result — +33.5% sales uplift over the trial period
- Mainstream Young Singles/Couples identified as the highest-value chip segment
- Backed a client-facing recommendation for Quantium's Category Manager
View Repository · Category Strategy Report
Python · Pandas · Tableau · 85,000+ trip records
End-to-end Python pipeline across 14 tables — analysing driver performance, route profitability, and fleet health. Packaged findings into an interactive Tableau dashboard for operational decision-making. Served as the capstone project for the TS Academy Data Analytics training programme.
Key findings:
- Fleet on-time rate of 55.7% against a 95%+ industry benchmark — systemic delivery failure
- One route running at –609% margin, requiring urgent investigation
- $5.7M in total maintenance spend mapped across the fleet
View Repository · Tableau Dashboard
Python · Pandas · Matplotlib · MySQL · SQLAlchemy · ETL Pipeline
Designed a normalised MySQL schema, built a Python/SQLAlchemy ETL pipeline to load 8,399 orders from Excel, then answered 10 self-generated business questions with Pandas analysis and Matplotlib visualisations across a 2009–2012 Canadian retail dataset.
Key findings:
- 50.4% of all order lines lose money — the single biggest operational risk in the dataset
- Furniture earns only 2.3% profit margin despite generating $5.18M in sales
- Discounts above 20% flip average order profit negative (-$249 avg)
- December and January are peak months — May–August is the consistent low season
SQL · MySQL · JOINs · Operational Risk Analysis
Analysed workload distribution, customer retention patterns, and supplier geographic concentration risk within a wholesale distribution business.
Key findings:
- Top 3 employees handled 52% of total orders — single-point-of-failure risk
- 6.7× workload gap between highest and lowest active employees
- 82% of supplier co-location concentrated in the USA and Europe
SQL · MySQL · Aggregation · Subqueries · Risk Analysis
Evaluated customer concentration risk, pricing imbalance, and inactive account revenue leakage within a wholesale distribution model.
Key findings:
- 17 inactive customers identified as a direct revenue recovery opportunity
- Pricing skew driven by premium product clustering inflating catalog averages
- Heavy geographic customer concentration flagged as revenue dependency risk
| Category | Tools |
|---|---|
| Query & Database | SQL · MySQL · Window Functions · CTEs · Subqueries · JOINs |
| Spreadsheet | Microsoft Excel · Power Query · Pivot Tables · Dashboard Design |
| Programming | Python · Pandas · NumPy · Matplotlib · Seaborn · SQLAlchemy |
| Visualisation | Tableau |
| Workflow | Git · GitHub · VS Code · MySQL Workbench · TablePlus · Jupyter Notebook |
DataCamp — Associate Data Analyst in SQL Industry-recognised, Associate-level certification confirming proficiency across the full analytics workflow — data preparation, exploratory analysis, and statistical reasoning in SQL. Credential ID DAA0015344805241 · View Credential · Certified Jul 2026.
TS Academy — Data Analytics (3-Month Certification Programme)
Completed a 3-month structured Data Analytics training programme covering the full analytics workflow.
Capstone project: Logistics Operations Performance Analysis. Certified Jul 2026.
Forage Job Simulations
| Programme | Issuer | Date |
|---|---|---|
| Data Analytics Job Simulation | Quantium | Jun 2026 |
| Data Analytics Job Simulation | Deloitte Australia | Jun 2026 |
| Data for Decision Makers Job Simulation | BCG | May 2026 |
IBM SkillsBuild — Data Analytics Pathway (2026)
Data Visualization and Presentation · Data Preparation for Analysis · Data Collection and Analysis · Inferential and Descriptive Statistics · Data Usability for Organizations · Data Classification · Data Fundamentals
I'm actively seeking Data Analyst roles in Credit Risk, Product, and CRM Analytics — where I can help businesses understand default risk, churn, and growth opportunities through SQL, Python, Excel, and Tableau, validated with statistical testing rather than assumption.
- 📧 salamitaofeek92@gmail.com
- 🌐 Portfolio — live reports and full project walkthroughs