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

71–80 of 178 posts

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

#71

Post by fredliu »

rl3 wrote: post #59
fredliu wrote: post #49

Earlier quoted context omitted.

By DL, i meant generic DL techniques like CNN, LSTM (used in this article), which relies on large amount of labeled data to train, and predict on similar data, thus my comment about automation. Alpha Go (Zero) is very specialized for the game of go, not sure how much of its specialized algorithm could transfer to other generic use cases.

> Alpha Go (Zero) is very specialized for the game of go, not sure how much of its specialized algorithm could transfer to other generic use cases. AlphaZero is a generalized successor, and it does just that: https://en.m.wikipedia.org/wiki/AlphaZero

Good to know it generalized, but seems it's only generalized on board games like problems where you have a problem space to search through, is that understanding correct? If so, it probably won't help in the use cases we are talking about here, right?

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

#72

Post by halayli »

You can use whatever prediction technique you like, but if your model is wrong, then so will the prediction. Predicting stock prices requires considering as many factors as you can gather that goes into setting the stock price, and how the factors correlate with each other.

> previous price of a stock is crucial in predicting its future price

This is a poor and incorrect model. The stock price has plenty other variables and many of which are unknown. What's used here is just a single variable.

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

#73

Post by alehul »

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…

Rentech and the other more secretive top quant firms such as TGS and PDT use nearly exclusively public data.

Funds like Two Sigma that haven't had as good (or scalable) returns are actually the ones that focus on novel data sources.

In reality, everyone in this industry is drowning in data, and the real edge comes from learning how to more efficiently parse and analyze data rather than acquiring more of it. The top performing firms work at a level where the data is merely an abstraction; above-market returns can be achieved from nothing but public data sources, if you've automated the process of extracting signals.

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

#74

Post by aggronn »

everdev wrote: post #35
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…

These predictions can also be self-reenforcing. If enough money believes the model is accurate, it will create it's own market conditions. In a distopian AI stock prediction world the best model will be the one with the widest publicity and adoption, not the best data points.

The problem I see with that hypothesis is that the asset pricing must eventually be tied to actual performance--while it may be self-reinforcing to some extend, if it _is_ fundamentally wrong, there will be a reckoning and an adjustment after a high value stock goes bankrupt, for example.

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

#75

Post by SEJeff »

turingcompeteme wrote: post #65
SEJeff wrote: post #29

Earlier quoted context omitted.

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?

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.

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

#76

Post by csomar »

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…

There is tons of opportunities in smaller markets that RT or others have no interest in, however.

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

#77

Post by lifeformed »

C1sc0cat wrote: post #50
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…

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

Well, being an employee gives you exclusive access to the best fund in existence by far (35% return every year for decades). Nobody is going to want to kill their golden goose.

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

#79

Post by eternalny1 »

I used to run a technical analysis site for exchange traded funds (ETFs).

Skipping to the "results" of this experiment, I am seeing nothing. It looks like a slow, short period moving average (SMA)... which does nothing in terms of predicting anything. It just averages out the chaos over time.

Post reply on HN