User Research | Figma | Adobe
HTML | CSS | JavaScript
Swift | React Native
Python | SQL | Tableau
Working with Cornell University Library on an ongoing research project focused on categorizing third-party privacy policies as “good” or “bad” based on transparency, data usage, and user protection standards. The goal of the project is to develop a scalable approach for analyzing complex legal text and supporting more informed decision making around third party services used by the library. The project explores the use of large language models (LLMs) such as ChatGPT and Gemini to assist with parsing privacy policies and generating structured datasets that can be used to train and evaluate machine learning models. Current work includes prompt design, dataset construction, and experimentation with AI assisted labeling techniques for natural language processing tasks.
Contributed to an applied machine learning research project focused on tracking urban carbon emissions by identifying, evaluating, and curating relevant datasets for analysis. My work centered on sourcing publicly available environmental and urban data and assessing data quality, coverage, and relevance to support downstream analytical and machine learning efforts. In addition, I researched urban solar radiation exposure by collecting and organizing surface level solar data across urban environments. This work supported broader efforts to understand spatial and environmental patterns in cities and helped establish a data foundation for future modeling and sustainability research.
