Welcome!
I’m Nneka Asuzu, a Data Scientist specializing in machine learning and end-to-end ML systems. I build, evaluate, and deploy models that drive real-world decision-making.
About Me
I focus on building machine learning models that uncover patterns in data and translate them into actionable insights.
My work spans the full modeling lifecycle from data preparation and feature engineering to model evaluation and deployment, ensuring solutions are practical, scalable, and effective in real-world decision-making.
Core Focus Areas
- Machine Learning: Supervised learning (regression, classification) and unsupervised learning (clustering, dimensionality reduction) using linear models, tree-based models (Decision Trees, Random Forest, Gradient Boosting, XGBoost), SVM, KNN, and PCA.
- Model Deployment & ML Systems: End-to-end ML workflows and deployment into cloud and production environments.
- Data Analytics & Statistical Methods: Exploratory data analysis, hypothesis testing, A/B testing, and time series forecasting (ARIMA, Prophet).
- Data Visualization & Business Intelligence: Power BI, Tableau, Plotly Dash.
- Tools & Platforms: Python (Pandas, NumPy, Scikit-learn), SQL, Git, Jupyter Notebook, Azure Machine Learning, Azure SQL Database, Power BI.
Achievements & Impact
- Improved model performance over baseline through feature engineering and hyperparameter tuning across multiple projects.
- Built and deployed machine learning models to support real-world decision-making.
- Designed dashboards that reduced reporting and analysis time by 30%, improving decision-making efficiency.
- Automated data workflows to improve consistency, reduce manual effort, and enhance data reliability.
Soft Skills
- Communication: Translate machine learning results into clear, actionable insights that support decision-making.
- Problem-Solving: Approach business problems using structured, data-driven thinking to develop effective ML solutions.
- Adaptability: Quickly learn and apply new tools, models, and techniques across different projects.
- Collaboration: Collaborate effectively with cross-functional teams to deliver machine learning solutions.
Featured Projects
- Credit Risk Prediction System – Classification (Logistic Regression → Random Forest → XGBoost), SHAP Explainability, Azure ML, Power BI
- Supply Chain Risk & Inventory Optimization – Classification (Logistic Regression → XGBoost → AutoML benchmarking), Azure ML, Power BI
- Customer Value & Lifecycle Modeling – Clustering (K-Means + PCA), Regression (XGBoost for CLV), A/B Testing, Streamlit
- Healthcare Workforce Optimization – Regression and Random Forest models for demand prediction, scenario simulation, and workforce planning under uncertainty