Main project: In many common fairness settings, we can’t observe counterfactuals — e.g. would a person we denied a loan pay it back if we had granted it? — and this biases training data, creating uncertainty particularly for groups historically denied loans.
Using techniques like structural equation modeling and infomax active learning, we seek to formalize whether getting labels (say, granting loans) for underrepresented groups or areas of our feature space for informational purposes could improve our model faster. This presents an explore-exploit tradeoff common in sequential decision problems, where we must balance doing what our model currently recommends with acquiring better training data.
Technically, using blavaan for Bayesian latent-variable modeling, and formulated likelihood function for our version of SEM
Used ML tools such as DeepLabCut and B-SOID on remote compute cluster, extracting pose information from mouse behavior video
Performed timeseries manipulation and analysis
Worked on projects studying neurological underpinnings of physiological arousal, mouse scent marking, and olfaction
Research Intern, UC San Diego Computer Science and Engineering
June 2021 — December 2021
Under Professor Christine Alvarado, studied the effects of ERSP, an early-undergraduate CS research program, on students’ senses of identity as researchers and computer scientists
Used thematic analysis methods on open-ended survey data, as well as Python for preprocessing, analysis, and interrater reliability calculation
Qualcomm Institute Learning Academy
September 2020 — December 2021
Along with another undergraduate, supervised by Leanne Chukoskie at the Qualcomm Institute at UCSD, conducted self-directed research project on engagement in online learning during COVID pandemic
Developed and distributed survey of UCSD students about their course experiences
Analyzed and visualized data in R, wrote most of paper’s Results section
Published in Frontiers in Education as co-first author