Machine learning in trading: theory, models, practice and algo-trading - page 1511
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
https://medium.com/datadriveninvestor/teaching-a-robot-to-buy-low-sell-high-c8d4f061b93d
on artificial data works as in the article, I ran it. But then everything again will be stalled by non-stationarity :)
Maybe if you take a differentiated stationary series from my article, it will be something interesting.
And yes, as far as cunneling works with MDP, now they try to insert LSTM layers to make the model have more memory. Sort of like the article by the author of this thread on Habra.
Yes, that's it! interesting, need to look into it.
Thanks!
Yes, that's it! interesting, I'll have to look into it.
thanks!
I think there was an article where he replaced the table with a neural network, look in his profile
There are several problems:
1. it is not clear how to determine the initial initialization parameters
2. Determining whether the state corresponds to the action, only by experience? There must be some objective criteria. We need to do some research,
The pictures look interesting.
If you highlight the signals and look at the resulting balance.
Good luck
Why do you need Gaussian? What is the global idea?
Why do you need Gaussian at all? What is the global idea?
In my TSthe probability density of increments, by some thinning of tick quotes, is practically reduced to the Laplace distribution.
This is done to make the market BP look like the Variance Gamma Process, for which all the math is known.
No one has ever really understood hmm, only at the level of dumb copying of libs? can't you rewrite it in mql? only the market is full of such neural network poop
and this is the basics by the way. i'll have to write an article again.
No one has ever really understood hmm, only at the level of dumb copying of libs? can't you rewrite it in mql? only the market is full of such neural network poop
This is the basics by the way. I'll have to write an article again.
Well, the libraries are not copied, but used (and they need to be used properly), and rewriting libraries in mql is for enthusiasts with lots of free time. Good luck in this hard Sisyphus work.
Well, libraries are not copied but used (and they need to be used properly), and rewrite libraries on MCL - is for enthusiasts with lots of free time. Good luck in this hard Sisyphean work.
+
Well, libraries are not copied but used (and they need to be used properly), and rewrite libraries on MCL - is for enthusiasts with lots of free time. Good luck in this hard Sisyphean work.
In fact, I sometimes envy Max Denisenko, his dependant position, sometimes you can be so fed up with work, up to nervous tics, go home at 3 am and not to the wife or children, where there, just lie down and immediately pass out, and at 8 again to get up and so on in a circle ...
On the other hand dependency is like the life of a plant, a vegetable, there are no problems or joys, it's like in Makarevich's song "fruit dessert". If you choose a short but eventful life of a hero, full of adventures, is better than the life of an overgrown dependent Max in a "golden cage", this is more for women, for kisses.
Ehhh.... The once-abusive thread.... Where are we going, huh? No answer...
The sorcerer, lying down on the edge of the forest,
Alyosha the son, beaten up by rogue investors,
The teacher working at the car wash,
TheGrail, obviously sitting near the church with his hand outstretched,
Fa (aka SanSanych), just becoming a loving grandfather to his grandson Kesha...
Where are you?!?!! Where is the brutality and desperate zeal?
Heh heh heh... Ugh.