Machine learning in trading: theory, models, practice and algo-trading - page 1842

New comment
 
Igor Makanu:

there's a great articleat https://www.mql5.com/ru/articles/1530

about statistical studies of TC results

I would like to make a similar calculation with NS

what is better to take as a training sample:

1. the results of transactionsP P P P P P P P P P P P P P P P P P P P P P U...

2. or values of statistics from tester (MO, Sharpe's coefficient, maximal series of profits/losses....) on several test periods

?

Good article.
It is possible to take the results for training, and so it is difficult to say what is better. It may be good as an additional filter.
 
Valeriy Yastremskiy:
Good article.
It is possible to take the results for training, and so it is difficult to say what is better. As an extra filter, it's fine.

I agree. Wonderfully laid out.

And how would your network look at such an option? The NS looks at the situation narrowly.

MN1

 

Understand one thing.

I am not here to destroy machine learning theory, but to understand and improve upon it to the best of my ability.

 
Uladzimir Izerski:

In the field of machine learning I have a complete zero and never said that I am proficient in this business. I am learning from you and from you.

The law is sacred. It is complicated in its description, it is not understandable to everyone.

First of all I haven't said anything to you about the Ministry of Defense. We talked to you exclusively about the market, and the law to which the price obeys I described above, but you seem too self-confident and independent in knowledge that would at least read it and try to understand. The discussion is over. Good luck !!!!
 
Mihail Marchukajtes:
Well first of all I didn't say anything to you about the MO. We talked to you exclusively about the market, and the law to which the price obeys I described above, but you seem too independent in knowledge that at least read it and try to understand. The discussion is over. Good luck!!!!

That's it. I'll shut up. And don't pour boiling water on me.

 
Uladzimir Izerski:

That's it. I won't say anything. And don't pour boiling water on me.

I don't mean it badly....
 
Such nonsense... it's not pleasant to read...
 
Uladzimir Izerski:

Understand one thing.

I have not come to destroy the theory of machine learning, but to understand and improve on my capabilities.

It's easier to understand from the history of NS
How neurons were discovered, who figured out how they work, who proposed the mathematical model, how learning came about. And also the history of econometrics to help. Who was the one who has proved that economic indicators are a little bit random?)
 
Valeriy Yastremskiy:
It's easier to understand from the history of NS
How neurons were discovered, who figured out how they worked, who proposed the mathematical model, how learning came about. And also the history of econometrics to help. Who ever proved that economic indicators are a bit random)

That's it, sorry. Just reading.

 
Uladzimir Izerski:

That's it, I'm sorry. Just reading.

You do not think, no one closes your mouth, just gathered here specific guys who can not tolerate demagoguery. Although AI systems have the ability to produce a non-obvious answer, but it's still an exact science where 1+1=2, rather than approximately, allegedly. So also the market is quite a specific type of activity where there are actual news, and there are pseudo teachings. Such as Yusuf's, for example.

Let's turn to Wikipedia, do you trust it?

Market- a set of processes and procedures for the exchange between buyers (consumers) and sellers(suppliers) of certain goods and services.

So maybe information about the relationship between buyers and sellers is important, rather than waves, stochastics, Bollinger, etc.? What do you think? You know, there are a lot of pseudo-experiments that are trying to take the first place.... I think I'll make another video, but this time it's a text. And with the sound, I think we need to come up with something normal. Damn, no one knows why gopro writes sound with noise????

1...183518361837183818391840184118421843184418451846184718481849...3577
New comment