MSc Data Science @ Pace University
From Sierra Leone, based in the United States

I am a data scientist passionate about building AI-driven, data-powered solutions that create measurable real-world impact—particularly in public policy, urban systems, finance, and social good.

📌 Focus Areas:
Data Science • Machine Learning • AI • Analytics • Decision Support Systems

🌍 Currently Building:
AfriRise Hub • Smile TV Africa • Data Assistant Pro

📫 Reach Me:
LinkedIn
Email

I work at the intersection of data, technology, and impact.
My strength lies in transforming complex, messy real-world data into clear, explainable insights that decision-makers can trust.

I enjoy end-to-end data science work—from problem framing and data integration to modeling, validation, and storytelling—especially on projects with policy, economic, or social relevance.

NYC Commercial Office Vacancy Risk Prediction

A large-scale, end-to-end data science project focused on predicting long-term commercial office vacancy risk in New York City following the rise of remote and hybrid work.

Why it matters:
The shift in work culture threatens billions in commercial property value and city tax revenue. This project provides a forward-looking, building-level risk assessment tool for city planners, policymakers, and real estate stakeholders.

• Integrated 6+ large-scale datasets (PLUTO, ACRIS, MTA transit data, business registry, zoning & building attributes)
• Engineered 15+ predictive features capturing physical, financial, and geographic risk factors
• Identified and resolved data leakage after detecting unrealistically high baseline performance
• Trained and evaluated multiple models:
  • Logistic Regression
  • Random Forest
  • XGBoost
• Selected models using AUC, Precision, and Recall with strong generalization (AUC ≥ 0.75)
• Built geospatial visualizations and SHAP dashboards to explain why buildings are high-risk

• Large-scale data integration & validation
• Feature engineering grounded in domain knowledge
• Data leakage detection & mitigation
• Model evaluation using business-relevant metrics
• Explainable AI (SHAP) for transparency and trust
• Translating ML outputs into policy- and finance-relevant insights

📌 Impact Insight:
Scenario analysis suggested that targeted interventions informed by the model could save ~$1.4M per planning cycle for NYC decision-makers.

• 🧠 MindMate AI (IBM Hackathon)
  Mental health triage assistant built with IBM watsonx, Flask, and agent-based AI concepts.

• 📊 Data Assistant Pro
  Enterprise-grade analytics platform for advanced data analysis, reporting, and AI-augmented insights.

• 💳 Loan Default Prediction
  Machine learning project supporting financial risk assessment and lending decisions.

• 🚦 Accident Hotspot Identification & Prediction
  Spatial and temporal data analysis to improve road safety and policy planning.

• 🎬 Smile TV Africa
  A media platform telling authentic African stories through film, data, and digital storytelling.

• 🌍 AfriRise Hub
  A platform empowering African youth with access to education, opportunities, and mentorship.

• Advanced Data Analysis & Visualization
  Python (Pandas, NumPy), Tableau, Power BI, Matplotlib, Seaborn

• Machine Learning & AI
  Scikit-learn, feature engineering, model selection, evaluation, explainability (SHAP), NLP fundamentals

• AI-Augmented Analytics
  LLM-assisted analysis, prompt engineering, decision-support workflows

• Applied Research & Impact Projects
  Urban analytics, financial risk modeling, accident prediction, public policy insights

• Communication & Storytelling
  Translating complex models into insights for technical and non-technical stakeholders

I work comfortably across classical ML, modern AI systems, and LLM-enabled workflows, with a focus on responsible, practical application.

• Machine Learning Foundations

  • Supervised & unsupervised learning
  • Bias, generalization, and evaluation
  • Feature importance & explainability

• Generative AI & LLMs

  • Prompt engineering for structured outputs
  • LLM-assisted data analysis and summarization
  • Using LLMs as analytical co-pilots
  • Understanding limitations (hallucinations, leakage, evaluation challenges)

• AI Systems Thinking

  • Retrieval-Augmented Generation (RAG) concepts
  • Human-in-the-loop AI design
  • Explainability, trust, and governance in AI systems
  • Ethical and policy implications of AI deployment

• Applied AI Projects

  • Agent-based AI (MindMate AI)
  • Decision-support systems (urban risk, finance, health)
  • AI-augmented analytics platforms (Data Assistant Pro)

I welcome collaborations, research discussions, and contributions.

To contribute:

1. Fork the repository
2. Create a new branch (git checkout -b feature/your-feature)
3. Commit your changes (git commit -am 'Add new feature')
4. Push to the branch (git push origin feature/your-feature)
5. Open a Pull Request

For questions or collaboration ideas, feel free to reach out via
LinkedIn or Email.

• 🎬 I write, act, and produce short films
• 🌍 I’m building a career at the intersection of technology, impact, and storytelling
• 🤝 Always open to mentorship, internships, and meaningful collaborations

“Let data tell the story — and let that story make a difference.”