Inspiration
We wanted to gain experience
What it does
Gives a forecast of what health outcome a person using a particular product will have
How we built it
Bert Sentence Embeddings and Multinomial Logistic Regression
Challenges we ran into
Selecting the right model for repeated measurement data (the same person has multiple logs). Ignoring this results in incorrect results.
Accomplishments that we're proud of
We accounted for the repeated measures of the dataset.
What we learned
New data wrangling approaches
What's next for FDA, Beginner Track, JAFS
Analyzing the infant data
Log in or sign up for Devpost to join the conversation.