Announcement_2025 11 20

I participated in the Erdős Institute’s Data Science Boot Camp. In addition to attending video lectures and completing exercises on the theory and practice of data science, I worked on a group project on developmental linguistics and language acquisition. We used developmental data from Stanford’s Wordbank dataset to engineer new features, added them to a dataset derived from the results of Duolingo users, and measured how much they improved predictions of second-language learning.

You can find our article, slides, and a video of our presentation here, and our code here.