Applied data scientist with experience building predictive models, analyzing large public datasets, and translating complex analysis into actionable insights. My work focuses on healthcare, public safety, and policy-related analytics where data can support better decision-making and improved outcomes.
Programming: Python, R
Data Analysis: pandas, NumPy, dplyr
Machine Learning: scikit-learn, XGBoost, Random Forest, Logistic Regression
Data Visualization: Matplotlib, Seaborn, ggplot2, Power BI
Data Management: SQL, SQLite, API integration
Methods: Predictive Modeling, Classification, Regression, Exploratory Data Analysis, Feature Engineering, Model Evaluation
I am a Medical Laboratory Scientist with five years of experience working in clinical environments and a graduate student in Data Science at Bellevue University. My background in healthcare has shaped my interest in using data to better understand health outcomes, public safety risks, and policy-related challenges.
Through my academic and independent projects, I apply machine learning, statistical analysis, and data visualization techniques to explore complex datasets and identify meaningful patterns. I am particularly interested in projects where predictive analytics can support real-world decision-making in healthcare, public health, and safety domains.
Regression modeling using Linear Regression, Gradient Boosting, and XGBoost to predict neonatal intensive care unit length of stay from admission clinical data.
View project →
Multi-class machine learning classification of seven migraine types using patient characteristics and neurological symptoms. Models evaluated include Logistic Regression, Random Forest, and XGBoost with SMOTE used to address class imbalance.
View project →
Machine learning models predicting pregnancy risk levels using maternal health indicators such as blood glucose, blood pressure, maternal age, and body temperature.
View project →
Logistic regression modeling using American Community Survey microdata to examine demographic and socioeconomic predictors of employment outcomes.
View project →
Large-scale traffic collision analysis using multiple public datasets to identify demographic and environmental risk factors associated with motorcycle accident severity.
View project →
Statistical analysis comparing mental health disorder prevalence across countries to examine variability and potential patterns in global mental health outcomes.
View project →
Policy-focused analysis examining childcare affordability relative to household income across U.S. counties, presented through a Power BI dashboard and data visualizations.
View project →
Data integration project combining CDC natality data with OpenFDA drug information to analyze patterns of medication exposure during pregnancy.
View project →
GitHub: https://github.com/eulafullerton
LinkedIn: https://www.linkedin.com/in/eula-fullerton-348842291/
Email: fullertoneula@gmail.com