About
I'm a data professional who loves solving problems and uncovering insights that drive real impact. With a background in finance, I bring a unique perspective that combines analytical thinking with business context.
I enjoy challenging myself with projects that allow me to grow. Recently, I built a Markov analysis model to predict monthly charge-offs with a margin of error of 2%. Using SQL and Python, I cleaned and transformed the data to capture the historical delinquency trends over time.
Outside of work, I’m passionate about growing my skillset through competitions and side projects. I competed in the NFL Big Data Bowl, using real in-game data to create a Random Forest Classifier that predicted the probability of the next play being a run based on the offense’s pre-snap movement. This achieved an accuracy of 80.9% and a ROC AUC of 87.4% on the test set. I also built an ETL pipeline that transforms Community Transit’s public GTFS data into a relational database.
As someone who’s been an end user in the data lifecycle, I understand the value of clean, organized data and the headaches when it’s not. Continuous improvement is central to how I work and approach life. I regularly attend local data meetups in the Seattle area to learn and share ideas.
Being a strong teammate is something I take pride in. I believe great results come from teams that build on each other's strengths. One of my proudest accomplishments is being the first in my family to graduate college while working two jobs, an experience that shaped my grit and determination.
When I'm not working with data, you'll usually find me exploring the outdoors around the Seattle area.
