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

Using a Keras Long Short-Term Memory Model to Predict Stock Prices

heartbeat.fritz.ai

Post reply on HN
Print view View original

171–178 of 178 posts

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#171

Post by just_some_guy10 »

turingcompeteme wrote: post #92
SEJeff wrote: post #75

Earlier quoted context omitted.

Most of them aren't hedge funds, they're private (HFT, Electronic Trading, Botique Firms, Proprietary Trading are all terms you'll hear) so they don't have public data. It is literally impossible to prove without insider information. However the Virtu Financials, the Citadels, etc, will always exist, and will be doing exceptionally well whether people realize it or not.

I realize this doesn't actually matter and I feel weird defending Renaissance... but Virtu is a public company and hasn't been doing that well, and returns from Citadel's various funds are not hard to find. Also, I don't know how to compare a fund's returns to that of a private business. But Medallion has been around since before HFT was really a thing, and I'm not aware of any HFT places that have been growing at 70…

It's not unheard of for market makers to have returns well above 100%, and one you get into certain latency arbitrage strategies the returns can grow significantly.

The issue is that these business are capital limited, so you can't reinvest your massive returns to compound them.

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#172

Post by bigmit37 »

sseveran wrote: post #128
jwiley wrote: post #102

Earlier quoted context omitted.

Can you clarify why "the target series should be log-normal returns" is important or provide a pointer for more information?

Here you go: https://financetrain.com/why-lognormal-distribution-is-used-...

Thank you.

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#173

Post by candiodari »

aggronn wrote: post #118
derefr wrote: post #105

Earlier quoted context omitted.

But the stock market isn’t just a bunch of people placing speculative bets about company performance; it’s a bunch of people placing speculative bets about company performance by buying shares of the companies . If the market is irrational, it can actually prop up companies that would otherwise go bankrupt.

I suppose they company could continuously issue stock in this case. But in this world, it actually makes sense for those companies to stop doing their normal business and just go into the business of selling their shares. This reality sounds absurd, but you could argue that BTC market is there. Enough of the market thinks that "always buy" is a good investment, regardless of the real-life value of the asset. Or maybe…

Both of those things have valid services that I pay for.

BTC provides a number of services. From money changing and international money transfers to actual investment brokerage. Granted, the number of securities available in BTC is less than spectacular, but it's not zero. I pay for both those services. Now you may argue that those are unregulated services and therefore have trust issues, but one might argue that all markets have trust issues, and the only difference is the level. BTC, so far, seems to be more trustworthy than, for instance, the ECB (e.g. the Greek payment limits and the Cypriot bail in, one of which affected me, and both of them used MY money to achieve political aims, without my approval).

Gold provides a store of value, with a good story behind it. I pay my bank, I believe, around $40 per year for that same service. With frankly, not as good a story behind it (as I trust my bank less than I'd trust a bar of gold under my pillow when it comes to still having value tomorrow. Not that I have the kind of spare change to make that a pressing issue, but ...)

So given that both BTC and Gold provide services that clearly people are willing to pay for, who's to say they shouldn't have a valuation based on that income like every other financial service provider in the world ?

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#174

Post by norswap »

> From the plot we can see that the real stock price went up while our model also predicted that the price of the stock will go up. This clearly shows how powerful LSTMs are for analyzing time series and sequential data.

Is laughter or tears the right reaction here?

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#175

Post by pcprincipal »

tomazio wrote: post #122
pcprincipal wrote: post #88

Earlier quoted context omitted.

I 100% agree with this as a Daily Fantasy Sports player who has published some blog posts and code related to strategy. Any success I've had has been in sports and formats that are not popular and I purposely do not write or open-source code on. Edge can go away almost immediately; I saw this firsthand in DFS when a number of websites came in with free tools that pros had been using for years. I play in the stock mar…

I'm very interested to read some of your blog posts related to strategy/code around DFS, but I don't know what your blog is. Would you mind posting a link to one of these posts?

Definitely, sorry for late reply. Here's a few:

- Pick Em strategies on DraftKings - https://medium.com/draftfast/evaluating-possible-strategies-...

- Thinking in multiples - https://medium.com/draftfast/thinking-in-multiples-7e7c76ee2...

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#176

Post by p1esk »

candiodari wrote: post #170
goodside wrote: post #140

Earlier quoted context omitted.

The problem isn’t that ML has gotten worse. It’s just as rigorous and far more powerful than it ever was. The problem is ML is hard, it hasn’t gotten orders-of-magnitude easier to understand, and there’s enormous incentive now to pass off amateur understanding as complete. The real ML still happens — it’s just drowned out.

I think people are saying that that's something they're not happy with. The big methods in AI, like backprop, 1) work a LOT better for specific problems than statistics or statistical learning ever has (and at this point, I think we can safely say: ever will) 2) a lot of methods either can't be explained, or outright shouldn't work, according to statistical theory. The use of statistics in machine learning is limited…

can't be explained, or outright shouldn't work, according to statistical theory

When people invented a steam powered engine, some other people had probably said: "Modern physics can't explain how it works. It shouldn't work. It's too complicated". Then a few decades later physicists discover laws of thermodynamics.

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#177

Post by nigealj »

goodside wrote: post #93

This is pure nonsense. This isn’t even the right way to begin thinking about this as a forecasting task — the target series should be log-normal returns, not raw asset price. The performance of this model is laughably bad, which is probably why he spends zero time evaluating its effectiveness. You could trivially get better forecasts than this by naively repeating the last-observed price . This isn’t ML. It’s cargo-c…

It's the AI winter we're all fearing!

Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices

#178

Post by timeseries2018 »

C1sc0cat wrote: post #52
hhmc wrote: post #47

Earlier quoted context omitted.

I'm shocked that would be even close to enforcable.

Me too I suppose if you where payed for life to not work in the field and would probably not be enforceable.

>> if you where payed

if you were paid

Post reply on HN