Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Numerai, a hedge fund built by a community of anonymous data scientists

medium.com

Post reply on HN
Print view View original

71–80 of 84 posts

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#71

Post by valdiorn »

lordnacho wrote: post #61

Quant fund insider here. The data is pretty pure, in the sense of not telling you any metadata at all. It's literally just a bunch of numbers and 0/1 labels. It's hard to implement a strategy without knowing what exactly you're looking at. I get the feeling this "pure dataset" is part of some framework that Numerai thinks will beat the market, given good predictors. That's not necessarily the case. Say I assume the 0…

> Say I'm right 70% of the time, then I can equal weight my bets and it will be just swell. But say I'm right about 51% of the time. Then it's going to take quite a while longer for the law of large numbers to work in my favour.

That's actually very far from being true. If you trade a single instrument, sure, the variance will kill you in anything but the very long run. But if you trade thousands of securities (like say, the entire US equity market), then a 55% prediction ratio and a market neutral strategy will absolutely crush. Even if you blindly buy/sell on every signal without doing any sort of weighing (excluding low confidence predictions, etc), then you should see a several sigma strategy.

It only takes a very, very small edge to make a very low risk strategy if you can diversify.

https://en.wikipedia.org/wiki/Signal_averaging

Now add on top of that the fact they will have several low SNR prediction signals, and the effects of signal averaging become even greater

I'm also a "quant fund insider", as you put it...

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#72

Post by oneloop »

brycehidysmith wrote: post #3
abcampbell wrote: post #2

But why did the machine want to go long Salmar ASA?

Does it matter? The machine saw a pattern, and it responded to the pattern. We don't need to know.

Yes, it does matter. Following the machine without understanding what's going on is how you make mistakes.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#73

Post by lordnacho »

valdiorn wrote: post #71
lordnacho wrote: post #61

Quant fund insider here. The data is pretty pure, in the sense of not telling you any metadata at all. It's literally just a bunch of numbers and 0/1 labels. It's hard to implement a strategy without knowing what exactly you're looking at. I get the feeling this "pure dataset" is part of some framework that Numerai thinks will beat the market, given good predictors. That's not necessarily the case. Say I assume the 0…

> Say I'm right 70% of the time, then I can equal weight my bets and it will be just swell. But say I'm right about 51% of the time. Then it's going to take quite a while longer for the law of large numbers to work in my favour. That's actually very far from being true. If you trade a single instrument, sure, the variance will kill you in anything but the very long run. But if you trade thousands of securities (like…

Yes, Taleb did the actual calculation in one of his books. I'm exaggerating because if I say it's 50.01% it will cause head scratching.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#74

Post by dzdt »

Some thoughts on the business model:

* traditional hedge funds have a problem with scaling: if you put more money in the same strategy returns go down. Numerai hopes to scale the number of strategies it employs by scaling the number of researchers participating.

* by providing researchers only opaque streams of data, they prevent researchers from leaving and competing directly. If you don't know how the data corresponds to the market, you can't replicate the trading at another fund. (Some big hedge funds like D.E.Shaw do the same!)

* researchers may still leave and compete indirectly, using the same algorithms on different market features. But by paying anonymously in bitcoin, Numerai may be hoping for the reverse, that programmers from other quant funds will anonymously moonlight for Numerai using their algorithms from those other funds.

* by being opaque with the data, Numerai keeps researchers from knowing the true value their strategies are providing. That information asymmetry is in Numerai's favor, letting them underpay even strong performers.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#75

Post by dharma1 »

HappyTypist wrote: post #66
dharma1 wrote: post #62

I've been looking at this a few times. Its like a giant ensemble. But I'm not sure ML will be able to beat chance on average on a data source like this. And if someone discovers they are making money consistently on numerai, I think they would set up their own fund quite quickly. I do like the encrypted system though, could be used for other ML competitions where you don't want to give your model away

I know why they're paying out Bitcoin and keeping everything anonymous. They are hoping quant hedge fund insiders submit their model to the site.

You don't submit a model, just results

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#76

Post by roel_v »

dzdt wrote: post #69
roel_v wrote: post #58

Earlier quoted context omitted.

"This is absolutely true. Many, many strategies that are viable at small portfolio sizes fall off very quickly when millions, tens of millions of dollars start to be used for them." I've thought this for nearly a decade now, yet have never seen or thought of such a thing. Of course I'm just an idiot so the fact that I didn't think of any means nothing; but you'd think that in all that time looking for it, someone som…

Dude, in the context of an internet post "this is absolutely true" MEANS "I think so too."

Sure, it was just a roundabout way of saying 'please elaborate' while trying to keep the tone non-combative.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#77

Post by mrkgnao »

onion2k wrote: post #51
modeless wrote: post #37

So in exchange for giving a hedge fund a stock tip that earns 20% in a month, the guy gets $10k? That sounds like a ripoff to me! If you have the skills to do that repeatedly you can make a whole lot more than $10k doing the trades yourself.

The point is that you probably can't do it repeatedly, or predict with any confidence that you can even do it once. Numerai enables you to bet using someone else's money, with a vastly reduced reward, but no risk to you. Numerai won this time (hence the PR piece) but I don't think we should judge their performance on one action in isolation. We should judge whether their approach works based on a year or two of tradi…

Plus, Numerai gives them opaque features for ML training that correspond to real-life data in ways that only Numerai knows. So you can't bail and use your model on your own.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#78

Post by nl »

TrickedOut wrote: post #32
fpgaminer wrote: post #28

I started poking at this out of curiosity, and a desire to begin sharpening my TensorFlow axe, and one thing remains unclear. They give you two spreadsheets, one being the training data and the other is the tournament data (what you need to predict on). Each entry in the spreadsheet is 21 features and a single binary class. The latter is what you predict. But for the submissions they request a probability, not a clas…

Have you found any good TensorFlow examples which handle financial or time series data like this? Please do share! Most of the examples I find are either image processing or text processing. Rarely time series or traditional DB type data.

Generally people use a LTSM for time series if they want to use a NN approach.

See http://robromijnders.github.io/LSTM_tsc/

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#79

Post by darawk »

wallace_f wrote: post #67
darawk wrote: post #56

Earlier quoted context omitted.

There are also 'experts' in these fields, so your point is moot.

OK, but how many physicists support the moon landing conspiracy? How many aerospace engineers support the moon landing conspiracy? What credentials do the experts of the moon landing conspiracy have that I should trust? I think he has a valid point if you have bias in which experts you place trust. There are, in fact, a lot of experts -- and even academically tenured, credentialed, published experts -- that I agree,…

Ya, true. There are particular areas though where 'wisdom of the crowds' works much better than any expert, and then there are obviously areas where it does not.

I'm not sure exactly what the properties of each type of problem are, but it doesn't seem at all obvious to me that stock picking is not one in which a sort of herd optimization approach might be very effective.

Re: Numerai, a hedge fund built by a community of anonymous data scientists

#80

Post by alexmingoia »

cryptokoala wrote: post #48

Numerai comes across as fraudulently abusing cryptographic buzzwords like homomorphic encryption https://medium.com/@Numerai/encrypted-data-for-efficient-mar...

Numerai uses order-preserving encryption, which is homomorphic. The algos are trained on the ciphertext itself.
Post reply on HN