🎓 Clinical Research Professional | Data Analyst in Transition to Data Science
💊 Experienced in medical and clinical research — now exploring how data and machine learning can drive better healthcare insights.
I have a strong foundation in clinical and medical research, where I’ve worked with study data, protocols, and analytical reports.
Today, I’m applying that evidence‑based mindset to data science, focusing on data exploration, statistical analysis, and machine learning to transform raw information into actionable insights.
I use SQL, Python, Excel, and Tableau (as my primary visualization tool on macOS) for analysis, and I’m expanding into machine learning and neural network modeling to build predictive solutions.
Overview:
This project analyzes the data analyst job market using SQL as the main analytical tool.
I explored:
- 💰 The highest‑paying data analyst roles
- 🔥 The most in‑demand technical skills
- ⚖️ The optimal skill mix balancing salary and demand
Key Insights:
- SQL is the single most critical skill in the job market.
- Python and visualization tools (Tableau, Power BI) complement SQL perfectly.
- Cloud & Big Data tools (Snowflake, PySpark, AWS) offer salary advantages.
- A balanced skill set of SQL + Python + Visualization + Cloud creates strong marketability.
Tools Used:
- PostgreSQL, SQL
- VS Code, Git & GitHub
“Turning job market data into career insights through the power of SQL.”
🔗 View on GitHub
🔗 View Dashboard on Tableau Public
Overview:
Interactive Tableau dashboard analyzing sales performance from 2013–2014. This project demonstrates effective data visualization, performance tracking, and business insight storytelling using real sales data.
Key Features:
- 💹 Visualizes monthly sales trends, discount bands, and regional performance
- 📊 Provides interactive filters for in-depth analysis
- 🔍 Highlights key sales patterns, top-performing products, and seasonal variations
Tools Used:
- Tableau Desktop & Tableau Public
- Excel dataset for sales data
- Data preparation and exploration in Python/Excel
“Transforming raw sales data into clear, actionable insights through interactive visualizations.”
🔗 View on GitHub
🔗 View Dashboard on Tableau Public
Overview:
A Tableau dashboard exploring Airbnb pricing, property types, and occupancy trends in Seattle.
This project demonstrates practical data visualization and storytelling using real‑world data.
Machine Learning Focus:
- Supervised Learning: Classification (Logistic Regression, KNN, Decision Tree, Random Forest, Naïve Bayes), Regression (Linear Regression, SVM)
- Unsupervised Learning: K-Means, Hierarchical Clustering
- ML Workflow: Data wrangling & manipulation (NumPy, Pandas), visualization (Matplotlib, Seaborn), building ML pipelines
- Churn Modeling: Predicting customer attrition
- Ensemble Models & SMOTE for class balancing
- Model Evaluation: Accuracy, Precision, Recall, F1-score, Overfitting & Underfitting detection
Neural Networks Focus:
- Activation functions, forward & backward propagation
- Perceptron layers, model training & evaluation
- Frameworks: TensorFlow & Keras
- Textual Data Preprocessing: Tokenization, vectorization, embeddings for NN
- Practical projects: Iris Classification and exploring text data for NN
Goal: Apply machine learning and neural network techniques to real-world datasets, build predictive models, and improve data-driven decision making.
- Advanced SQL for analytics
- Python for data science workflows
- Machine Learning & Neural Networks for predictive modeling
- Text Data Processing & Analysis
- Data storytelling through visualization and reporting
| Category | Tools |
|---|---|
| Data Analysis | SQL, Python (NumPy, Pandas, Matplotlib, Seaborn), Excel |
| Visualization | Tableau |
| Databases | PostgreSQL, MySQL |
| Machine Learning | Scikit‑learn, TensorFlow, Keras |
| Research Expertise | Clinical & Medical Research, Study Design, Data Reporting |
| Text Analytics | NLP Preprocessing, Vectorization, Embeddings |
- Applying machine learning techniques to healthcare and business data
- Exploring neural networks for prediction and pattern recognition
- Building ML pipelines and automation workflows
- Designing interactive dashboards for communication of insights
“Bridging the gap between research and data science — one dataset at a time.” 💡