News for hackers. Stuff that matters.
Re:Jane Street Market Prediction ($100k Kaggle competition) by quantumofalpha on Tuesday November 24, 2020 @06:24PM (#25204222)
On a frozen feature set and evaluation dataset, sure. 3000+ competitors vs a few employees at JS who prepped this data. In light of very noisy data, the chances are not really on JS side here. But would the best model still be as useful on novel out of sample data is very questionable

Market prediction is low signal-to-noise problem, what's much more likely the contest will be an exercise in overfitting and the final shake up will be yuuuge.

There are no comments on this comment yet.