“Making data make sense—one line of code at a time.”
I’m a data analyst and scientist who enjoys digging into messy data and finding interesting stories that hide inside. I’ve always been curious about how things work, and data gives me the perfect excuse to ask questions, explore patterns, and build some cool stuff.
Originally from Fonda, NY and now living in Richmond, VA. Before moving to Richmond, I studied at the Rochester Institute of Technology where I received an Bachelors Degree in Economics ('13) and then a Masters in Business Administration ('14). Most recently, I completed a Masters in Data Science ('25) from Old Dominion University, where I concentrated in Business Intelligence Analytics.
Currently I work as a Business Insights Lead for the Private Label team at McKesson Medical Surgical. I’ve worked on all kinds of projects—from building predictive models and automating reporting to creating interactive dashboards that make data easy to understand (and kind of fun to look at). I use tools like SQL, Python and PowerBI daily, and I’m always experimenting with new ways to make data more useful and accessible.
When I’m not wrangling and exploring data, you’ll probably find me out and about with my wife and my two daughters enjoying the wide array of things Richmond has to offer. Always open to collaborating or chatting about all things data!
Capstone Project for Masters Program in partnership with Jefferson Labs. By leveraging historical sensor data, waveform signals, and system logs of the Spallation Neutron Source (SNS), created models to help detect potentially errant beams that would damage the system.
Final Project for ODU CS625 - Data Visualization, collected data from publicly available sources for Medicare, Pharmacies and Department of Energy. The data was then cleaned and merged to analyze through visualizations created with VegaLite.
With over a decade of SQL experience, I’m comfortable creating and modifying tables, writing complex queries, and using CTEs to keep data tasks efficient and organized.
4 years of experience using Python for data pre-processing and analysis, with a focus on cleaning, transforming, and analyzing datasets using libraries like pandas and NumPy.
Experienced in creating impactful visualizations and dashboards using Tableau, Power BI, and the Microsoft Office suite. Skilled in turning complex data into clear, actionable insights for diverse audiences.
Proficient at exploring data to identify patterns, trends, and insights that drive smarter decisions. Experienced in making sense of complex datasets in distribution and sales to reveal meaningful stories and support business goals.
This project was completed as part of my coursework in CS: 620: Intro to Data Science and Analytics. In this project, Python libraries were employed to investigate chronic illness trends along with a focus on prediction modeling to evaluate correlations between ashma rates and air qualty across the United States. The Google Colab notebook with all work done for the project can be found here.
For this introductory course, data was explored using basic Python code to process and clean the dataset, create columns for feature engineering and finally to create visualizations. The Google Colab notebook with all work done for the project can be found here.
This project leveraged machine learning and other analytic methods to predict response times to incidents by the San Francisco Fire Department. To process the data, Spark SQL was utilized to pre-process the raw data that was then fed into a Random Forest model in PySpark. The Google Colab notebook with all work done for the project can be found here.
The code was developed to read through a list of financial new headlines, generate the n-grams, and then train various models to determine which model performed the best at generalizing unseen data. Repo with all work done for the project and how to utilize code can be found here.
For this code, it was developed to read through a compilation of 1.6million tweets, from Kaggle dataset Sentiment140 dataset with 1.6 million tweets, create various language models and attempt to predict if the tweet had a positive or negative sentiment. Repo with all work done for the project and how to utilize code can be found here.
Built an encoder & decoder models using the Wikipedia Sentences & AG News datasets by tokenizing the sentences and preparing input–output pairs, trained the model using cross-entropy loss with teacher forcing to improve learning, and evaluated model using perplexity metric. Enocoder script located here, and Decoder script located here.