Machine learning in trading: theory, models, practice and algo-trading - page 2928
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
The MO says close the shorts on the Jew and look for a buy...
There's a good chance of a rise for 2-3 days
MoD is bullshit, it'll leave you out of money in a heartbeat.
Half a year to buy the eur, minimum.
I need a good help on ONNX.
Despite the fact that its name comes from neural networks (Open Neural Network Exchange), it can be used for saving other models, for example, trees(LightGBM). I wonder if the local implementation will support all such models.
It seems to be possible to create a model almost manually and save it in this format, not only from MO packages.
It seems to be possible to create a model almost manually and save it in this format, not only from MO packages.
Is it still necessary to generate data for prediction+preprocessing using mql tools? Or can we just use Ohlc and do all the complex preprocessing in Onnx as well?
It seems, yes, the whole data processing pipeline can be put there. But I am not ready to give a hundred per cent guarantee, I have only gone through the top of the topic so far.
Good afternoon, everyone,
I know that there are enthusiasts of machine learning and statistics on the forum. I propose to discuss in this topic (without holivars), share and enrich our own knowledge bank in this interesting field.
For beginners and not only there is a good theoretical resource in Russian: https: //www.machinelearning.ru/.
A small review of literature on methods for selecting informative features: https://habrahabr.ru/post/264915/.
I propose problem number one. I'll post its solution later. SanSanych has already seen it, please don't tell me the answer.
Introduction: in order to build a trading algorithm, it is necessary to know what factors will be the basis for predicting price, or trend, or the direction of opening a trade. Selecting such factors is not an easy task, and it is infinitely complex.
I did not see any specific suggestions on the first page. You do not have to tell your secrets if you are a master in using machine learning for trading. But you can give links or attach materials.
I think that the attached outline is well suited for this task. There is a PDF file in the archive.
It seems, yes, the whole data processing pipeline can be put there. But I'm not ready to give a hundred per cent guarantee, I've only gone over the top of the topic so far.
Well, if yes, then it turns out that any code can be ported at all, not necessarily the model, and it's really cool.....
There are probably some limitations, both in the format itself and in its specific implementation. But still I hope that it will simplify the use of MO in real trading, especially when VPS is used.
Surely there are some limitations, both in the format itself and in its specific implementation. But still I hope that it will simplify the use of MO in real trading, especially when VPS is used.
Also the possibility of testing TS on MO in MT5 tester. In general, a working ONNX will greatly reduce bicycle building and crutch production.