Hi trev, nice work on the competition so far! Thanks for the questions.
I won't go into how exactly the data is divided (just to keep things fair). I'll just say that we mixed a couple strategies to make sure it was representative of how the algorithm would be used in the future. That is, the new data coming in will never look exactly like the data you already have.
The visible public leaderboard is not the final score (so that people can't just overfit what they see there). It is calculated on a subset of the test data. I think the explainer for this is buried in the rules--we'll make sure to call that out more prominently.
Thanks for the question! The nonprofit, Education Resource Strategies, has put up the prize pool for this competition. For them, there's a clear operational win in being able to do this work more effectively and efficiently. A smart solution means that they can better serve the schools and school districts they partner with.
Good question. Those are both organizations we admire and good touch points for what we do.
We think of our mission as having two parts. The first is to provide high-quality machine learning to organizations with a social impact. The second is to show aspiring and practicing data scientists the really important (and really cool) questions they can tackle in the social sector. We're organized as a social enterprise because we believe it's the most sustainable way to make these things happen.
