Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Yeah, I’m arguing to not disclose the model. It’s worth far more held close.

If you want to work at Jane Street, go work for Jane Street. If you want to build your own models and run your own shop, the tools exist for you to do that without Jane Street (although there’s probably some amount of value learning the ropes there while they pay you, if that’s your thing).

My comments in thread are primarily around not having someone’s work exploited by sophisticated hedge/prop trading/investment professionals, which I’ve seen happen more than once, and for which you have no recourse.



My point is the winning model of the competition will not be worth anything beyond the prize. It will only be the best amongst other kagglers, almost none of whom are domain experts in finance. It will not stand a chance in "prod".


Assuming it passes some absolute measure(s) of quality. You could be the best on Kaggle and still have a mediocre model.


A backtested model is similar to a great startup idea. There is a huge amount of work to be done before it is worth much.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: