Machine learning in trading: theory, models, practice and algo-trading - page 1178
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
Nah, I mean, what do you teach? - The packet-liba? I thought it was about the network.
https://www.mql5.com/ru/forum/261479/page16#comment_8011085
To avoid the dilemma, it is necessary to use your own tester with a fully controlled structure. In this case there is full confidence that the tests will not differ significantly from the real work.
agree
Well then I wrote that in this case it does not matter which side is the trace and which side is the test
I remember, in your case the further into the past the test the better, in trading it's all individual
So, not to repeat, publish your own experience, and at the same time you will prove that the market is unchanging
Aha! Finishing the finishing touches and on github, and then right away for the proof of "market immutability", you have very insightfully understood what I meant, I would not have guessed it myself, thank you.
Aha! Finishing the finishing touches and on to github, and then right away for the proof of "market immutability", you very insightfully understood what I meant, myself would not have guessed, thank you.
please, but keep in mind on githab screenshots from Vorontsov's lectures won't work:)
a treasure trove of all sorts of ML approaches for the market :) the contest is still going on
https://www.kaggle.com/c/two-sigma-financial-news
Ivan Negreshniy, I don't understand something, here I created model in CatBoost, and how it is supposed to be connected, is it the organization of bridge/channel from EA to python, on which the predictor values will be transferred, and in the opposite direction the result of calculations will be received - a concrete class?
As far as I understand, CatBoost allows to unload the code of the model, which I do not understand, but I will attach it for professional estimation, can it not be integrated in MQL somehow and not use python then? And, the CatBoost has libraries in C++, they can not make it work in MQL and do not use python or console commands?
And, CatBoost has libraries in C++, you can't make them work under MQL and then not use python or console commands at all?
Of course you can. Everything is possible.) You have a C++ library, write an interface for MQL and you're good to go.
But for Python, the interface is universal and can be used with all Python libraries. (But the interface for CatBoost can't be used for anything else, and it would be a pity to throw it away).
Of course you can. Everything is possible). There is a C++ library, write an interface for MQL, and it's done.
Except that for Python, the interface is universal and suitable for all Python libraries. And the interface for CatBoost can do nothing but that, and it would be a pity to throw it away).
Well, show the man, you already have everything done there on python, show me how to connect the catbusta, figure it out
then I will connect and show you how to teach the model
Well, show the man, you already have everything done there on python, show me how to connect the catbusta, figure it out
Then I will connect and show you how to teach the models
I wrote a few posts above, that I have implemented the Python-Lua connection via client-server, I haven't connected to MQL yet.
With MQL it's easier - you just have to remove unnecessary things. If you remove it yourself, I can send you C++ instances of DLL for Lua with the client and TCP server.