Jane Street Market Prediction ($100k Kaggle competition)
1–10 of 217 posts
Re: Jane Street Market Prediction ($100k Kaggle competition)
#2Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering.
If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets.
Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
Re: Jane Street Market Prediction ($100k Kaggle competition)
#3Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
You don't have to (and certainly won't) beat all of Jane Street. The goal is to beat everyone else on Kaggle. A still difficult but much more accomplishable task.
Re: Jane Street Market Prediction ($100k Kaggle competition)
#4Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
You don't have to (and certainly won't) beat all of Jane Street. The goal is to beat everyone else on Kaggle. A still difficult but much more accomplishable task.
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.
Re: Jane Street Market Prediction ($100k Kaggle competition)
#5Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
'Admittedly, this challenge far oversimplifies the depth of the quantitative problems Jane Streeters work on daily, and Jane Street is happy with the performance of its existing trading model for this particular question'
Re: Jane Street Market Prediction ($100k Kaggle competition)
#6Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
>Jane Street has spent decades developing their own trading models and machine learning solutions to identify profitable opportunities and quickly decide whether to execute trades. These models help Jane Street trade thousands of financial products each day across 200 trading venues around the world.
>Admittedly, this challenge far oversimplifies the depth of the quantitative problems Jane Streeters work on daily, and Jane Street is happy with the performance of its existing trading model for this particular question. However, there’s nothing like a good puzzle, and this challenge will hopefully serve as a fun introduction to a type of data science problem that a Jane Streeter might tackle on a daily basis.
Sounds like it's just for fun/recruiting rather than trying to crowd source new strategies -- I'm sure if they were looking to crowd source strats they'd pay a whole lot more than 40k for first place
Re: Jane Street Market Prediction ($100k Kaggle competition)
#7So, if I parsed the training data correctly, one's output algorithm is completely agnostic to any actual market conditions. It's merely learned on the anonymized feature set of 130 variables. Making it qualitatively no different that any other abstract ML forecasting problem. There's no considerations of market microstructure, news driven events, leverage, etc?
Re: Jane Street Market Prediction ($100k Kaggle competition)
#8Any model superior to what Jane Street is running is worth vastly more than the prizes they’re offering. If you prove such a model out, get licensed (SEC, FINRA) and start soliciting to manage assets. Disclaimer: Not investment advice. Not a lawyer, not your fiduciary.
True, and I don't think they expect models that are superior to their own, I'd look at this as a hiring / marketing tool. Plus, even if you had a model that from a pure engineering standpoint was able to match Jane Street's approach, the model would not work without the wealth of proprietary (and expensive) data sources that Jane Street is sure to ingest, so you still couldn't just go out and do it yourself without some serious upfront investment first to get the same data. That is assuming all data they use is even available commercially, which I doubt as well. There are probably data sources that only become available to you through personal relationships with the right folks at the right places.
Re: Jane Street Market Prediction ($100k Kaggle competition)
#9Just give me some monkeys, darts and a dart board
Re: Jane Street Market Prediction ($100k Kaggle competition)
#10Earlier quoted context omitted.
You don't have to (and certainly won't) beat all of Jane Street. The goal is to beat everyone else on Kaggle. A still difficult but much more accomplishable task.
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 havi…
Assuming it passes some absolute measure(s) of quality. You could be the best on Kaggle and still have a mediocre model.