Oluwasegun Raphael

About Me

Data Scientist and Analyst with 3+ years of experience delivering end-to-end analytical workflows across telecom, finance, healthcare, agriculture, and public sector domains. I specialize in Python, machine learning, and statistical analysis; building reproducible pipelines that go from raw data to actionable business decisions. Experienced in prompt engineering and LLM evaluation workflows, with a proven track record of translating complex analytical findings into insights that drive measurable impact.

  • Programming & Analysis
    Python (NumPy, Pandas, SciPy, Statsmodels, Matplotlib, Seaborn, Scikit-learn, TensorFlow), SQL (SQL Server, MySQL, SQLite)
  • Machine Learning
    Regression, Classification, Clustering, A/B Testing, Feature Engineering, Model Validation, Predictive Modeling
  • Web Scraping & Automation
    BeautifulSoup, Selenium, Requests, data extraction from dynamic and static web sources
  • Visualization & Reporting
    Tableau, Power BI, Excel, PowerPoint, Google Sheets
  • GenAI & Emerging Tech
    Prompt Engineering, LLM Evaluation, AI Model Training, Data Annotation
  • Tools
    GitHub, Git, Jupyter Notebook, VS Code, PyCharm, Jira, Confluence
  • Soft Skills
    Stakeholder Communication, Technical Documentation, Business Insight Generation, Team Leadership, Cross-functional Communication
  • AI Data Trainer, Data Annotator & Prompt Engineer — Remote | Contract
    Mindrift | Surge AI | Alignerr
  • Data Analyst — Hybrid
    National Agricultural Seeds Council (NASC)
  • Data Training & Technology Administrator — On-site | Contract
    Society for Family Health (SFH)
  • Data Quality Assessor — On-site | Contract
    ACHIEVE, Pact
  • B.Tech, Marketing & Management Sciences
    Ladoke Akintola University of Technology — June 2021

Projects

Customer Churn Prediction

Customer Churn Prediction Pipeline

End-to-end ML pipeline predicting telecom customer churn; 3 models compared (Logistic Regression, Random Forest, Gradient Boosting), 85% ROC-AUC, risk segmentation, and statistical inference with Statsmodels. Includes a step-by-step walkthrough notebook for learners.

Web Scraping Retail Analytics

Web Scraping & Retail Analytics Pipeline

Automated end-to-end Python scraping pipeline extracting 1,000+ books across 50 categories using BeautifulSoup and Requests; multi-page pagination, data validation, structured CSV/JSON output, and EDA. Includes a step-by-step notebook for collaborators.

A/B Testing Analysis

A/B Test: Customer Retention & Revenue Optimization

Designed and executed an end-to-end A/B testing framework (20,000 simulated customers) applying z-tests and t-tests to evaluate discount strategy impact on churn. Built revenue impact models and delivered an executive-ready consulting report.

Agricultural Climate Impact

Agricultural Performance & Climate Impact Analysis

Developed an end-to-end environmental impact analysis on agricultural yield using Python (Pandas, NumPy, SciPy), applying independent t-tests to quantify yield differentials. Built an interactive Power BI dashboard with DAX-based KPI modeling.

SuperStore Analysis

Super Store Sales & Profitability Analytics

Built an end-to-end Python data pipeline to ingest and transform multi-sheet retail data, engineering derived features including profit margin and discount tiers. Delivered a four-page interactive Power BI dashboard with executive KPIs and geographic profitability mapping.

Insurance Claims Analytics

Insurance Claims Risk & Customer Analytics

Built predictive analytical models on insurance claims data to identify high-risk customer segments and fraud indicators. Delivered an interactive Power BI dashboard with real-time KPIs on claim volume, approval rates, loss ratios, and customer segmentation.

Return Home

Contact Me

ralpholuwashegun@gmail.com

+234 704 471 1492

Download CV