Bachelor of Science in Computational Data Science
Minor in Mathematics
GPA: 3.5/4.0

Starting soon!

Collaborated in a team of 10 to perform Exploratory Data Analysis on geographic satellite data, resolving missing values and ensuring high-quality data for model training.

Spearheaded the implementation of the Data Acquisition Pipeline, transforming high-resolution geographic raster files into training-ready images.

Engineered a pipeline using Deep Learning to create region-specific climate forecasts for different climate change scenarios.

Managed GPU cluster operations, including Data Migration to external storage and code adaptation for cluster compatibility.

Communicated key findings to stakeholders, effectively bridging the gap between technical and non-technical audiences.

Developed a Feature Selection package in Python implementing a variety of feature importance and filtering schemes based on tree-based ML algorithms like XGBoost and CatBoost, and could be used in a Scikit learn Pipeline that reduced boilerplate code in the ML pipeline and increased performance by a factor of 4.

Created a data visualization of a dataset representing the purchases and interests of nearly 235 million American consumers by geographic location with Plotly, querying data from Google Cloud Platform.

Increased the performance of a consumer long-term value model implemented in Pytorch by 8 through feature selection and replacement of an old dataset on AWS EC2 instances.