I am a Ph.D. candidate in Technology and Social Behavior, a joint Ph.D. program in Computer Science and Communication Studies at Northwestern. I work with Prof. Jessica Hullman at Midwest Uncertainty Collective (MU Collective).
My research investigates effective means to quantify and communicate prediction uncertainty inherent in machine learning models, aiming to enhance human-in-the-loop, data-driven decision-making. For instance, how can we better understand individual decision-making and aggregate social welfare in shared prediction contexts where predictions can influence the outcomes they try to predict? How can we process the uncertainty in network predictions where the occurrences of predicted ties can be dependent on each other? How do we make predictions and their associated uncertainty more explainable and transparent for "Black-Box" AI Models?
My research produces tools and insights that enable users to make more informed decisions, thereby enhancing the efficiency of system outcomes. By adopting an interdisciplinary mixed-method approach, I utilize ML/AI models to dissect and understand large, complex systems. This process entails designing intuitive uncertainty visualizations and conducting extensive, large-scale online experiments.
Before starting my doctoral study at Northwestern, I received a B.A. in Economics and a B.A. in Statistics from UC Berkeley and later an M.A. in Computational Social Science from UChicago. You can find my academic CV and one-page résumé here.