Data-Science-Portfolio
Hi, I’m [Asia Sabiu Sulaiman] 👋
Data Scientist & Health Tech Analyst | Kano, Nigeria 🇳🇬
Human Physiology graduate applying data science and machine learning to solve real-world problems in health, business, and advisory contexts.
🧬 About Me
- 🎓 B.Sc. Human Physiology — [Bayero University, Kano]
- 📜 3MTT Data Science & Machine Learning Certificate — Federal Government of Nigeria
- 📊 Microsoft Power BI — Currently studying (PL-300)
- 🎯 Targeting roles in Technology Advisory, Health Data Science & ESG Analytics
- 📍 Based in Abuja, Nigeria — open to remote opportunities
🚀 Featured Project
🛒 Supermarket Sales Prediction App
Built and deployed a live machine learning web app that predicts supermarket transaction sales using a tuned Random Forest model.
What makes this project stand out:
- ✅ Identified and fixed data leakage — a critical ML integrity issue
- ✅ Feature engineering — extracted hour, day of week, month & weekend flag from raw Date/Time
- ✅ Hyperparameter tuning with RandomizedSearchCV (5-fold CV)
- ✅ SHAP explainability — communicated model predictions to non-technical stakeholders
- ✅ Live Streamlit deployment — real users can interact with the model
- ✅ 6 actionable business insights for inventory, staffing & pricing decisions
Python Scikit-learn Random Forest SHAP Streamlit Pandas Seaborn Power BI
🛠️ Tech Stack
languages = ["Python", "SQL", "R (basic)"]
ml_tools = ["Scikit-learn", "XGBoost", "Random Forest", "Gradient Boosting", "SHAP"]
data = ["Pandas", "NumPy", "Feature Engineering", "EDA"]
viz = ["Matplotlib", "Seaborn", "Power BI", "Plotly"]
deployment = ["Streamlit", "Git", "GitHub", "Google Colab", "Joblib"]
domain = ["Human Physiology", "Clinical Data", "Health Analytics", "Biostatistics"]
🎓 Certifications
| Status | Certification | Issuer |
|---|---|---|
| ✅ Completed | B.Sc. Human Physiology | [Bayero University, Kano] |
| ✅ Completed | Data Science & ML Certificate | 3MTT — Fed. Govt. Nigeria |
| 🔄 In Progress | Microsoft Power BI (PL-300) | Microsoft |
| 📅 Planned | Google Data Analytics | Google / Coursera |
| 📅 Planned | Azure AI Fundamentals (AI-900) | Microsoft |
| 📅 Planned | AWS Cloud Practitioner | Amazon Web Services |
🗺️ What I’m Building Next
- 🦠 Disease Outbreak Prediction — ML model using Nigeria NCDC & WHO datasets
- 🏦 Financial Fraud Detection — Anomaly detection for KPMG Audit & Risk use cases
- 📊 Supermarket Power BI Dashboard — Interactive business intelligence report
- 🏥 Hospital Readmission Risk Predictor — Clinical ML model using patient data
💼 What I Bring to the Table
I sit at a rare intersection — biomedical knowledge + data science skills. Most data scientists lack domain expertise in health and life sciences. Most health professionals lack technical ML skills. I bring both.
This makes me particularly effective in:
- 🏥 Health Tech & Clinical Analytics — I understand the data I’m working with
- 🌱 ESG Analytics — science background helps interpret environmental & health data
- 🔍 Audit & Risk Analytics — anomaly detection and data integrity assessment
- 💡 Technology Advisory — translating ML outputs into business recommendations
📬 Let’s Connect
📧 Email | 💼 LinkedIn | 🌐 Portfolio Website
“Data without domain knowledge is just numbers. Domain knowledge without data is just intuition. I build the bridge between both.”