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

81–90 of 178 posts

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

#81

Post by throwawaymath »

DevX101 wrote: post #26

I'm not a purist believer in the efficient market hypothesis. BUT, I doubt there's much alpha to be gained simply from looking at price data which is widely and publicly available. Also keep in mind that markets are dynamic feedback loops so even if this model had an edge, the act of publishing this article would work against you to neutralize that edge in the future. There's a good reason the most successful 'quanti…

I'm pretty sure that lifetime NDA is a myth. It gets repeated very often (like a lot of the Renaissance mythos) but I haven't seen evidence for it, and on its face it sounds flagrantly unenforceable. It could be that the compensation alone substantially reduces turnover. Likewise once they've hit "their number", employees may decide to go into tech or philanthropy instead of a competing firm.

For what it's worth, Renaissance (remarkably, in my opinion) advertised a role in the most recent Who's Hiring thread.

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

#82

Post by throwawaymath »

SEJeff wrote: post #75
turingcompeteme wrote: post #65

Earlier quoted context omitted.

Bigger sure, but can you point to one that has had better performance than the medallion fund?

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.

Yeah, a better name for these kinds of funds is "independent research groups." Edgestream is an example of another. Renaissance is the most (in)famous one, but many others exist which profitably manage tens to low hundreds of billions while employing only 10 - 100 people.

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

#83

Post by nabla9 »

DevX101 wrote: post #26

I'm not a purist believer in the efficient market hypothesis. BUT, I doubt there's much alpha to be gained simply from looking at price data which is widely and publicly available. Also keep in mind that markets are dynamic feedback loops so even if this model had an edge, the act of publishing this article would work against you to neutralize that edge in the future. There's a good reason the most successful 'quanti…

> Rennaisance Technologies is so secretive and subjects its employees to a lifetime NDA/non-compete.

Medallion fund is profit maker but their strategy is obviously very size limited. Their strategy does not scale.

Betting syndicates can make similarly massive ROI, but they are very growth limited.

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

#84

Post by throwawaymath »

all2 wrote: post #42
dointheatl wrote: post #24

11:15, restate my assumptions: 1. Mathematics is the language of nature. 2. Everything around us can be represented and understood through numbers. 3. If you graph these numbers, patterns emerge. Therefore: There are patterns everywhere in nature.

> Everything around us can be represented and understood through numbers. One of the biggest problems facing someone trying to assemble a numerical model of some thing or process is whether or not their model is adequate to describe the phenomena they are observing. This is why psychology remains a statistically modeled science, largely relegated to anecdotal research. (Note that my intent is not to speak ill of psyc…

Well said. Having to add increasingly many edge cases to your model is a sign your model is insufficient.

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

#85

Post by spongepoc »

samfisher83 wrote: post #58

All these LSTM Stock Market tutorials seem to be a variation of this guys tutorial which he did a while ago: https://github.com/jaungiers/LSTM-Neural-Network-for-Time-Se... Except Jakob explains the folly of the method. Whereas the author of this piece says the following: 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 show…

>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.

Yes I've noticed on HN recently ML and data science have become popular topics but I'm surprised a post like this has so many votes.

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

#86

Post by JohnJamesRambo »

nabla9 wrote: post #83
DevX101 wrote: post #26

I'm not a purist believer in the efficient market hypothesis. BUT, I doubt there's much alpha to be gained simply from looking at price data which is widely and publicly available. Also keep in mind that markets are dynamic feedback loops so even if this model had an edge, the act of publishing this article would work against you to neutralize that edge in the future. There's a good reason the most successful 'quanti…

> Rennaisance Technologies is so secretive and subjects its employees to a lifetime NDA/non-compete. Medallion fund is profit maker but their strategy is obviously very size limited. Their strategy does not scale. Betting syndicates can make similarly massive ROI, but they are very growth limited.

What is a betting syndicate?

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

#87

Post by jefftk »

minimaxir wrote: post #19
levesque wrote: post #2

Pretty underwhelming. From the very limited experiment demonstrated, the LSTM seems to be playing catch up rather than actually predicting trends.

I noticed this as well. Many data science thought pieces don't quantify the results, and it's suspicious that they're not included in detail (typically, the R^2 of a simple stock market prediction model is super low, making it impractical putting actual money on the line as it's barely better than guessing randomly : https://twitter.com/minimaxir/status/1021885939361042432 )

> barely better than guessing randomly

In the stock market something that is consistently better than guessing randomly is very valuable! You don't need much of an edge to make a lot of money.

(I'm very skeptical about approaches like the OP though)

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

#88

Post by pcprincipal »

DevX101 wrote: post #26

I'm not a purist believer in the efficient market hypothesis. BUT, I doubt there's much alpha to be gained simply from looking at price data which is widely and publicly available. Also keep in mind that markets are dynamic feedback loops so even if this model had an edge, the act of publishing this article would work against you to neutralize that edge in the future. There's a good reason the most successful 'quanti…

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 market a little and my best wins have been on small cap stuff where I've had some edge with unique knowledge of the industry and have taken the time to read SEC filings / keep tabs on earnings reports / closely watch competitors, acquisitions, etc.

To be clear, I still think this article is great from a learning about Keras perspective. That said, to anyone who thinks building some ML models and outperforming the market is easy, remember that edge is only as good as the number of participants in the market who don't have it.

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

#90

Post by TomK32 »

JohnJamesRambo wrote: post #86
nabla9 wrote: post #83

Earlier quoted context omitted.

> Rennaisance Technologies is so secretive and subjects its employees to a lifetime NDA/non-compete. Medallion fund is profit maker but their strategy is obviously very size limited. Their strategy does not scale. Betting syndicates can make similarly massive ROI, but they are very growth limited.

What is a betting syndicate?

For example this one https://news.ycombinator.com/item?id=16985413
Post reply on HN