What it does

Predicts the revenue produced by users in the following week when they install an app.

How we built it

Using python in VSCode, with pyTorch and other tools.

Challenges we ran into

Pre-processing, memory issues and a very sparse dataset.

Accomplishments that we're proud of

We got to first of the leaderboard after a long night of working in a long pipeline that led to our final model and preprocessing.

What we learned

Using dask as a data loader to deal with a way bigger datasets than we could otherwise.

Built With

Share this project:

Updates