Tolúwanimí Awófisáyọ̀
Mathematics graduate with hands-on experience in data analysis across healthcare, finance, telecommunications, and e-commerce. Skilled in Excel, Power BI, SQL, and Python — with a portfolio of 4 completed projects analyzing datasets of up to 130,000+ records. Passionate about turning raw data into clear business insights that drive smarter decisions.
Education
Olabisi Onabanjo University (OOU)
Bachelor of Science (B.Sc.)
Relevant Coursework: Data Analysis & Computation, Statistical Methods, Business Mathematics
Skills
Data AnalystExcelPower BISQLPythonPivot tablesdashboardsKPI cardsslicersdata cleaningData modelingDAX measuresinteractive dashboards(SSMS)SELECTGROUP BYCASE WHENHAVINGaggregate functionsPandasMatplotlibSeabornStatistics & MathematicsDescriptive statisticsprobabilityanalytical reasoning
PORTFOLIO PROJECTS
Healthcare Fraud Detection
Tool: Microsoft Excel | Domain: Healthcare
Analyzed 10,000 healthcare claims to identify fraud patterns across providers and insurance types Built an interactive Excel dashboard with 4 charts, 6 KPI cards and 4 slicers for dynamic filtering Key finding: Fraudulent claims averaged $990 vs $535 for legitimate claims — an 85% difference, indicating inflated billing as the primary fraud tactic General Practice providers showed the highest fraud rate at 9.69% across all specialties
Loan Default Risk Dashboard
Tool: Power BI | Domain: Financial Services
Analyzed 130,138 loan records to identify key drivers of default risk across DTI, income, credit score, and loan size Built an interactive Power BI dashboard revealing counterintuitive insight: small loans default at 37% vs 22% for large loans Key finding: High income borrowers had the highest default rate at 40%, proving income alone is an unreliable risk predictor
Customer Churn Analysis
Tool: SQL (Microsoft SQL Server) | Domain: Telecommunications
Wrote 9 SQL queries analyzing 1,000 telecom customers to identify churn drivers and high-risk customer profiles Key finding: Month-to-Month + Fiber Optic + No Tech Support customers churned at 57% — over twice the overall churn rate Identified 3 complaints as the critical tipping point — beyond which churn rate jumps from 25% to 36%
Amazon E-Commerce Sales Analysis
Tool: Python (Pandas, Matplotlib, Seaborn) | Domain: E-Commerce
Analyzed 128,975 real Amazon India orders to uncover revenue trends, category performance, and regional insights Key finding: Sets and Kurtas account for 77% of 78.6M total revenue, representing significant category concentration risk Identified B2B customers as an untapped opportunity — higher average order value (₹701 vs ₹648) but less than 1% of total revenue
CERTIFICATIONS & TRAINING
Python for Beginners & Intermediate
Data Analysis with Python
Completed
Power BI Fundamentals
Self-directed learning with applied project
ADDITIONAL
Cowrywise Campus Ambassador
Promoted financial literacy and investment awareness among students
Data Hub Ambassador
Community engagement in data and analytics education
Web3 Enthusiast
Active interest in blockchain technology and decentralized finance