I use data and machine learning to understand how people learn, and build tools that actually help them do it better.
I'm a sophomore at Carnegie Mellon studying Statistics and Machine Learning. Most of my work sits at the intersection of data and human behavior. I'm interested in what the numbers reveal about how people think, learn, and make decisions, and what you can actually do with that.
Right now I'm a research assistant at the OAK Lab building ML pipelines to analyze how learners discover rules, and I've been doing UX and data work for EdTech programs on the side. I'm looking for opportunities in data science, ML, or AI broadly. EdTech is where I've spent most of my time, but I'm genuinely interested in any domain where data can do something useful.
Real-time facial Action Unit detection from 478 MediaPipe landmarks to classify learner engagement and trigger adaptive feedback. Includes a personal calibration system with deviation-based dead zones to account for individual baseline variance, something most automated engagement tools ignore.
Trained a machine learning model on 360k+ trip records to predict hourly bike demand across 40+ stations, hitting 70.21% accuracy. Used systematic feature selection and hyperparameter tuning in scikit-learn to get there.
Mixed-methods research with school counselors and district decision-makers to surface why career ed software doesn't get adopted. Synthesized findings via affinity diagramming and journey mapping into stakeholder outreach materials.
Designed and automated pre/post survey pipelines to generate individual growth profiles and cohort-level STEM confidence summaries for grant reporting. Built transformation logic to track longitudinal skill confidence changes across the program.
I'm actively looking for internships in data science, machine learning, or AI for summer 2027. I've been working mostly in EdTech but I'm open to other domains. If you're doing interesting work with data, I'd love to hear about it.
hiabigaillo@gmail.com