April 30: Live interview on ABC-7 WJLA about our work modeling COVID-19 [video]
I am a PhD student in Computer Science at Harvard University, studying how machine learning and optimization can solve challenges in public health. My work currently focuses on developing predictive models and sequential planning tools for community health workers in India combatting tuberculosis. I have also worked on models for simulating non-pharmacological interventions for preventing the spread COVID-19 and designed machine learning models for detecting sobriety using mobile health data (check out the dataset!) Before computer science, I studied computational genetics as a Pelotonia fellow.
In the Summer of 2018, I interned with Spatial.AI, a tech startup breaking into the space of geosocial data. There, I designed NLP pipelines with Python to compute “social scores” for cities using geotagged social media. I also built predictive models based on these social scores and demographic data to estimate success of retail store fronts.
I was hired in 2014 by a bussing company that decided it was time to stop managing all of their data with Excel. I designed for them a Microsoft Access Database to handle hundreds of assets and equipped it with a custom schedule system for drivers. Little did I know that this would spark my love of computer science! I still provide technical support and regular updates for my best customers, and probably will until Microsoft goes out of business.
Everyone needs a way to relax. I do it by beating a (my own) drum. And sometimes I even get the chance to do it on stage! Music is a life-long passion of mine that I am always looking to exercise.
My research currently lies at the intersection of machine learning, optimization and public health. This has led me to technical interests in sequential planning paradigms including Markov Decision Processes and Restless Bandits, particularly in online learning settings. My application-based interests are in the challenges that arise from making AI tools work for community health workers in the field, especially in low-resource contexts. I am also broadly interested in data science problems that leverage human-generated behavioral data to derive insights focused on improving health.