Machine learning in trading: theory, models, practice and algo-trading - page 564
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
Here's what I was thinking. There are a lot of implementations of all sorts of networks, but there are all sorts of complex formulas. If someone can "decipher" them, then I can encode them in µl. Then you can feel the different methods.
How do you like this suggestion?
Or I will study it myself and then I will not show it to anyone)Here's what I was thinking. There are a lot of implementations of all sorts of networks, but there are all sorts of complex formulas. If someone can "decipher" them, then I can encode them in µl. Then you can feel the different methods.
How do you like this suggestion?
Or I may study it myself and won't show it to anyone later)No, such a suggestion).
There is a bunch of already written software for the use of NS. You debug the system and connect it to MQL through API. From MQL, the delivery of data and trading functions is required. And you don't have to write anything.)
No way, such a suggestion).
There is a bunch of already written software for applying NS. There, you debug the system and connect it to MQL via API. From MQL, the delivery of data and trading functions is required. And you don't have to write anything).
No way, such a suggestion).
There is a bunch of already written software for applying NS. There, you debug the system and connect it to MQL via API. From MQL, the delivery of data and trading functions is required. And you don't have to write anything.)
You've already said that. I am not accustomed to trust somebody else's code, maybe it has errors or even is incorrect. It seems to me that I still need to understand what you're testing, what the point is there.
So my way out is to learn Python or R and then look through the libraries to understand what's there.
By the way, even without neural network the curvature on futures is not much worse than yours.
By the way, I came largely thanks to you. When I was just starting out, it was you who gave me the link to Reshetov's article. The article, in general, is nothing, rather as an example of application, but it became approximately clear where to harness the horse.
I do not know, whether there are such methods in Google, as I myself have finally come to Monte Carlo.
I don't know about RL either, but from your brief description it sounds like my methods.
I found Monte Carlo in Google -https://logic.pdmi.ras.ru/~sergey/teaching/mlbayes/08-neural.pdf Only this is completely different.
i will google m-c more articles tomorrow, i don't know it, so i have to read it.
Here is a primer, but I will read it tomorrow :)
http://fxtreder.ru/foreks/stati/537-praktikum-dlya-trejdera-sistemnyj-trejding-otsenka-torgovykh-sistem-metodami-monte-karlo.html
You already said that. Well, just not used to trust other people's code, what if there are errors or even wrong. It seems to me all the same need to understand what you're testing, what the meaning is there.
So my way out is to learn Python or R, and then see what's in the libraries to understand.
In the alglib library, which comes standard with the terminal, there's already a multilayer Perspectron and a random forest... experiment, you don't need to write anything. These are essentially basic models, the rest in other packages are just additional tweaks on top, and the basis is used the same.
the alglib library, which comes standard with the terminal, already has a multilayer perseptron and a random forest... experiment, you don't need to write anything. These are essentially basic models, the rest in other packages are just add-ons on top, and the basis is used the same.
I'll try to unwind and explore, what's the random forest called in the library or is there a name for it specifically?
I'll try to unwind and explore, what is the random forest called in the library or is there a name there specifically?
CDecisionForest
helphttp://alglib.sources.ru/dataanalysis/
You already said that. Well, just not used to trust other people's code, what if there are errors or even wrong. It seems to me all the same need to understand what you're testing, what the meaning is there.
So my way out is to learn Python or R, and then see what's in the libraries to understand.
The modern concept of OOP implies that you can (or even shouldn't) know absolutely nothing about the inner workings of objects. Only the interface.
Thus ignorance of the device of an electric kettle does not prevent its use.
Usually such software is well documented, already tested by thousands of users and there is no doubt about its performance.
As for Python or R, I can not say anything, because I do not use it for NS. As for internal terminal libraries in terms of scaffolding and NS, IMHO, not the best choice.
CDecisionForest
helphttp://alglib.sources.ru/dataanalysis/
Thank you. It will be something to study.