Discussing the article: "Developing a robot in Python and MQL5 (Part 2): Model selection, creation and training, Python custom tester"

New comment
 

Check out the new article: Developing a robot in Python and MQL5 (Part 2): Model selection, creation and training, Python custom tester.

We continue the series of articles on developing a trading robot in Python and MQL5. Today we will solve the problem of selecting and training a model, testing it, implementing cross-validation, grid search, as well as the problem of model ensemble.

In the previous article, we talked a bit about machine learning, performed data augmentation, developed features for the future model and selected the best of them. Now it is time to move on and create a working machine learning model that will learn from our features and trade (hopefully successfully). To evaluate the model, we will write a custom Python tester that will help us evaluate the performance of the model and the beauty of the test graphs. For more beautiful test graphs and greater model stability, we will also develop a number of classic machine learning features along the way.

Our ultimate goal is to create a working and maximally profitable model for price forecasting and trading. All code will be in Python, with inclusions of the MQL5 library. 

Author: Yevgeniy Koshtenko

 

Good article. I like that everything is done in the "classic" MO way, without any subtlety.

Didn't quite realise yet, on a quick look, what ensemble of models are being built. Were they trained on the same or different data.

I'll figure it out later and add to it.

 
Awesome article! Thanks a lot to the author for his work! This series becomes the main one for me to get acquainted with python))) Didn't have much interest before, all the pros and mcool))
 
Maxim Dmitrievsky #:

Good article. Like that it's done in the "classic" MoD way, no subtle stuff.

Didn't quite realise yet, on a quick look, what ensemble of models are being built. Were they trained on the same or different data.

I'll figure it out later and add to it.

Thank you very much, very nice! The ensemble is trained on the same data)

 
Aleksandr Seredin #:
Awesome article! Thanks a lot to the author for his work! This series becomes the main for me for the purpose of acquaintance with python))) Didn't have much interest before, all the pros and mcool)))

Thank you! Thank you!

 
What a waste of Python syntax highlighting in articles(
 
Thanks for the article! I read it with interest. I'm also planning to take advantage of learning different Python models in the future, and here is actually a ready-made recipe that gives a good base to start from.
 
Yuriy Bykov #:
Thanks for the article! I read it with interest. I'm also planning to take advantage of learning different Python models in the future, and here is actually a ready-made recipe that gives a good base to start from.
Thank you very much, Yuri!
 
Yuriy Bykov #:
Thanks for the article! I read it with interest. I am also planning to take advantage of learning different Python models in the future, and this is actually a ready-made recipe that gives a good base to start from.
I read your articles with great pleasure too. In the future I plan to make a multi-currency version of my algorithm, so the topic of your articles is very interesting and useful!
 

Thanks to the previous article, I went to learn python.

I have not had time to make much progress in understanding python, and here is the second article, and it is interesting too.

And I'm like in the fable - the fox and the grapes))))

 
Good motivation when there are results!
And, as I realised, it's not a week ahead, and not a month, but a normal year's worth of work
12
New comment