I am pursuing a B.S. in Data Science with a minor in Economics at Lehman College, CUNY. My interests include data analytics, data engineering, machine learning, public-interest technology, and making complex information easier for people to understand and use.
My technical journey began with web development through All Star Code and Code Nation, where I learned how to plan, design, and build interactive websites and applications. I originally joined Lehman for Full Stack Web Development due to these experiences.
I continued developing those skills through CodePath Web Development 101 and Web102, progressing from HTML, CSS, and JavaScript to React applications, API integration, routing, state management, interactive visualizations, and Supabase-backed projects.
As my interests developed, I became increasingly interested in the information behind applications: how data is collected, organized, analyzed, modeled, and communicated. This led me to switch my major to Data Science at Lehman College and complete Code the Dream Python 100: Data Analytics, where I worked with Python, Pandas, ETL workflows, relational databases, and analytical dashboards.
I am currently strengthening my knowledge of machine learning, data engineering, artificial intelligence, and cloud computing through Code the Dream Python 200.
My projects span public health, mental-health access, housing affordability, human resources, customer retention, education, retail, sports, and economic analysis. I am especially interested in projects that serve a practical or community purpose and translate technical findings into accessible tools.
- Lehman College, CUNY — B.S. in Data Science, Minor in Economics
- Code the Dream — Python 200: Data Engineering, AI and Cloud
- Code the Dream — Python 100: Data Analytics
- CodePath — Technical Interview Preparation 101
- CodePath — Web102: Intermediate Web Development
- CodePath — Web Development 101
- Code Nation — Web Development 1 and 2
- All Star Code — Introduction to Web Development
Extended a county-level composite index comparing relative mental-health need and provider availability across 10 Metro Atlanta counties.
- Created supplemental capacity-gap analyses and priority rankings
- Produced correlation, capacity, and geographic visualizations
- Examined methodological limitations and county-level data availability
- Built an interactive decision-support website using the analytical outputs
Explore the live website · Website repository
Developed and evaluated a Random Forest classification model for predicting customer churn.
- Examined class imbalance and classification thresholds
- Evaluated accuracy, precision, recall, F1 score, and confusion-matrix results
- Considered the business consequences of missed churn cases and false alerts
Built an ETL workflow and interactive dashboard for exploring relationships between Major League Baseball performance statistics and team wins.
- Gathered, cleaned, transformed, and organized baseball data
- Examined statistical relationships with team performance
- Presented results through an interactive Streamlit application
Analyzed more than 50,000 retail records covering over 3,000 products.
- Compared international markets and regional order activity
- Examined product diversity and customer purchasing frequency
- Translated grouped analysis into business-focused observations
Python · Pandas · NumPy · SciPy · scikit-learn · Matplotlib · Seaborn · Plotly · Tableau · Excel · Jupyter · Google Colab
SQL · PostgreSQL · Supabase · SQLite · ETL · Prefect · FastAPI · Pydantic · REST APIs · Web Scraping · Selenium
React · TypeScript · JavaScript · HTML · CSS · Vite · TanStack Router · Leaflet · Recharts
Git · GitHub · Docker · VS Code · Streamlit · Lovable
- Data cleaning, transformation, aggregation, and validation
- Exploratory and descriptive analysis
- Correlation analysis and hypothesis testing
- Linear, polynomial, and logistic regression
- Classification and Random Forest models
- Cross-validation and model evaluation
- Time-series analysis and forecasting
- Feature selection, PCA, and multicollinearity analysis
- Composite-index construction and normalization
- Dashboard, heatmap, scatterplot, and choropleth-map development
I want to continue developing the connection between software, data, and real-world decision-making. My goal is to contribute to teams where I can:
- Build reliable and understandable data workflows
- Analyze information across different domains
- Develop tools that make findings easier to explore
- Communicate technical results and limitations clearly
- Continue strengthening my statistical, engineering, and machine-learning foundations
