Self-Taught Data Science Learner • Public Health & Clinical Data Analyst
I develop actionable insights from clinical and epidemiological datasets, focusing on maternal health, risk stratification, and community health analytics.
I combine Python-based reproducible workflows with statistical and machine learning approaches for public health research.
- Data Cleaning & EDA: Transform raw clinical and survey data into actionable insights
- Epidemiological & Clinical Modelling: Risk stratification, outcome prediction, and disease-stage analysis
- Visualization: Structured dashboards and charts for publications and reports
- End-to-End Research Projects: From data acquisition → cleaning → analysis → interpretation → insights
- Self-Learning: Continuous skill growth through real datasets and public health projects
- Exploratory Data Analysis (EDA)
- Data Cleaning & Wrangling
- Hypothesis Testing & Risk Factor Analysis
- Regression Models (Linear, Logistic, Cox)
- Classification & Regression
- Tree-Based & Ensemble Models
- Feature Engineering & Selection
- Model Evaluation (Accuracy, F1, ROC, AUC)
- Self-Learning Discipline
- Clear Conceptual Breakdown
- Reproducible & Clean Code
- Translating Analysis into Public Health Insights
- ML • Predictive Modelling • Python • Statistics
- SQL • R • Data Cleaning • Visualization
- Deloitte Data Analytics Job Simulation
- Web Dev Basics (Git, VS Code)
- Public Health & Maternal Health ML Projects
- Strengthening Python, R & SQL Skills
- Learning Deep Learning for Healthcare Data
- Improving Tableau Dashboards for Epidemiology
- Practicing End-to-End Research Workflows
📧 Email: shanzaykhan3002@gmail.com
🔗 LinkedIn: https://www.linkedin.com/in/shanzaykhan-/
💻 GitHub: [Your GitHub link]
⭐ Always learning. Always improving. Always building for public health impact.