Is this graph at the end a one-step-ahead prediction? Because if it is, then it looks very much like a 50/50 success/failure ratio. Which is what I would expect, because otherwise you could extract a signal from it.
Using a Keras Long Short-Term Memory Model to Predict Stock Prices
41–50 of 178 posts
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#4211:15, 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 psychology and its cohort, only illustrate that just because you can slap numbers on a thing doesn't mean you've described it well.
Look at the transition of understanding from Newtonian mechanics to relativity and quantum mechanics. Newtonian mechanics was enough until someone saw Mercury was doing weird things it shouldn't.
And before Newtonian mechanics we had a broken description of the solar system with more exceptions than rules. We were throwing numbers at a system and failing, in some part, to describe it with consistency.)
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#43Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#44wonder 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.
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#45Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#46The problem with these types of systems are it's difficult to do backtesting on a single continuous data stream... I write about that here: https://blog.projectpiglet.com/2018/01/perils-of-backtesting... I recommend doing something similar to the original post. Neural networks tend to produce valid looking output for a stock price easily, a random walk does too. You have to find correlations, causations, and then rev…
Interesting but i am a non believer can you provide figures that show gains through years?
Added in an edit update - I have more, but just tossed some together for you from 2016 - 2018.
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#47I'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…
How does a lifetime non-compete work?
I'm shocked that would be even close to enforcable.
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#48Do 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 basically exist and have existed within a massive bubble of misinformation since forever. There's a reason order flow is so valuable.
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#49Total 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…
DL isn’t just good at automating human tasks (see AlphaZero and AlphaGo). It can be used to recognize patterns and train to solve problems better than humans. Though in this case since the market is people making predictions about a prediction I’m not sure how much it’d help. There’s probably something about humans using a rough estimate of what the stock has been historically to inform where it could go though so it…
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.
Re: Using a Keras Long Short-Term Memory Model to Predict Stock Prices
#50I'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.