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

61–70 of 178 posts

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

#61

Post by zugweg »

fredliu wrote: post #56
zugweg wrote: post #36

Earlier quoted context omitted.

I think relating DL with human skills is confusing you. DL already beats humans in recognizing dog breeds. DL could always do a better job, because it looks at more patterns than humanly possible.

The reason I relate human skill with DL, is because for tasks where there are real patterns that humans can consistently recognize, DL is applicable, because it relies on human labeled inputs. For patterns, even humans can't consistently recognize (or if there are patterns at all), there's no way for DL to be better than humans, simply because the inputs from human can't be trusted. The example of DL does better job…

I think you are still confused. Replace DL with software.

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

#63

Post by fredliu »

rl3 wrote: post #32
fredliu wrote: post #25

Total noob question in this space (algotrading with DL algorithms). What DL is good at, is to automate tasks that are easy for humans (e.g. telling cat from dog, understand a sentence from sound wave, translation, etc) but hard for machines without DL. Now, if a task is even hard/borderline impossible for humans to achieve (e.g. predicting stock market with higher accuracy and consistency), why would we believe DL co…

Because there's no requirement that deep learning must only excel at tasks humans are good at. That said, the pitfalls of using ML in trading systems are numerous.

I didn't mean it's a requirement, but a fact that what ever DL could do is based on its input (labeled data), and that input has to come from human, or the task underneath is possible for human.

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

#64

Post by jermaustin1 »

DevX101 wrote: post #53
C1sc0cat wrote: post #50

Earlier quoted context omitted.

A lifetime noncompete really I assume they pay you for life for this noncompete.

My understanding is that legally, the contract says something reasonable, like a year. But the firm will use it's considerable resources to impede your career if you attempt to work in mathematical trading after that year's up. On the flip side, employees are compensated very well, and the turnover is very low.

I'd assume turn over is low if by leaving they now have to change entire career paths. I'd put up with a lot of shit to not have to learn a brand new trade.

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

#65

Post by turingcompeteme »

SEJeff wrote: post #29
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 is one large quantitative trading firm, there are other bigger and more successful ones however. I happen to work for another very large and successful quant trading firm.

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

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

#67

Post by auganov »

caymanjim wrote: post #44
gcb0 wrote: post #30

wonder how effective those models will become when everyone starts believing in those models to do trades.

The vast, vast majority of trading is fully automated algorithmic already.

Of which almost all is HFT. And by definition HFT has to be fully automated. I'm not sure if there's any data on the kind of algorithmic trading that the article talks about.

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

#68

Post by mishurov »

gaius wrote: post #34

Oblig XKCD https://xkcd.com/1570/ Seriously tho', articles like this need to come with a big banner at the top saying warning: do not try this at home .

Quite the opposite.

People in finance are much more advanced in terms of mathematical statistics and numerical methods, they use time series analysis, stochastic calculus, etc.

Keras is a high level framework for lazy people or for prototyping maybe, this is for trying at home.

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

#69

Post by abakker »

jermaustin1 wrote: post #64
DevX101 wrote: post #53

Earlier quoted context omitted.

My understanding is that legally, the contract says something reasonable, like a year. But the firm will use it's considerable resources to impede your career if you attempt to work in mathematical trading after that year's up. On the flip side, employees are compensated very well, and the turnover is very low.

I'd assume turn over is low if by leaving they now have to change entire career paths. I'd put up with a lot of shit to not have to learn a brand new trade.

They make SO much money, though, and get access to the special employees-only fund, so I assume that employees that join are interested in staying.

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

#70

Post by zugweg »

rl3 wrote: post #48
zugweg wrote: post #28

Do not minmax scale the data. New data outside ranges seen before will be chopped off. Do make relative (high/low), so patterns you find generalize to other domains. Don't fit complex LSTM models on tiny datasets. Somehow this is the shiny thing all starters jump on, while the most simple models are the most proven and robust. Don't just share such a model without giving a disclaimer ("I never tried this out on real…

> This is real money, real economies, and you could horribly crash these. That is also why you don't write with authority about how to build a bridge ... Setting aside that first bit of hyperbole, I don't see the danger in the bridge example. I mean, if engineers are building bridges based on information they've gleaned from internet articles, there are larger issues at play. As far as markets, retail traders basical…

ML is dangerously overhyped (that is an issue at play). This article uses min max scaling, so it will treat a 30$ stock as if it were 20$. You want someone like that managing your pension fund?

I refer to engineering code, because it is clear to me we don't want our bridges build by those not skilled enough to make safe bridges. Yet, it is not so clear with ML/AI, while the potential for damage may be even greater.

https://en.m.wikipedia.org/wiki/Financial_Modelers%27_Manife...

Post reply on HN