Machine learning in trading: theory, models, practice and algo-trading - page 2360
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
I.e. the task is to win crumbs of quality gain through a significant increase in time, model enumeration
but there is also an auto preprocessing and auto exploratory analysis
(And you can probably also optimize them.) A person also behaves differently in different situations. Moreover, this behavior is also programmatic.)
The person also behaves differently in different situations. And this behavior is also programmatic.)))
modern MI trumps reason in the choice of models.
Modern MO trumps reason in model selection
In the speed of selection)
by the way, about the editor for working with code, here is from personal experience: started with nodepad++, then sablim, then various interlages etc., then put VSCode and realized that everything before that was just crap.
the only thing that microsoft made for the world useful is VSCode
I'll soon roll out an interesting product, I had to deal with javascript + nodejs + vue + npm + pm2 + express + a couple of js bibles on rendering graphs.
By the way, about the editor for working with code, from my experience: started with nodepad++, then sablim, then all sorts of interlages and so on, Then I put VSCode and realized that everything before it was just bullshit.
the only thing that Microsoft made useful for the world was VSCode.
Oh, cool.
I see you've been through a lot))
Has anyone tried to look at the market in this way?
Construct a model based on supports and resistances built on the approximated price.
I think it's an interesting approach, and most importantly, it can be formalized
In the speed of the overkill)
in the choice of models
Has anyone tried to look at the market in this way?
Build a model based on supports and resistances built on the approximated price.
I think it's an interesting approach, and the main thing is that it can be formalized.
How do you approximate it?
How do you approximate it?
Fourier, I take the sum of the first n (2-5) harmonics with the largest amplitude
I try something like "one shot learning" but in my own way, or simply, I try to look for complex patterns...
I give one rebound and many "not rebounds" in the proportion of about 1 to 200, so it is like a training with one example, then I take probability from the model and look at the new data what happens to the price when the model shows higher probability...
It's almost the same as comparing the current price with my own pattern and look at the closeness measure, only here I look at the model probability...
Frankly speaking, sometimes it is very good, although there are not many deals but it is only one pattern and there may be many of them
Here is an example of one successfully found pattern, the first one is a kind of train, all the others are new data
Looks good to me.