Machine learning in trading: theory, models, practice and algo-trading - page 3485

New comment
 
Maxim Dmitrievsky #:


0.00381. That's pretty good. Of course, it is not 0.035.) But it is not evening yet.)
As for profit, you can have it on anything that is better than SB.) But in this case we are not talking about profit, it is not for realisation.
 
Maxim Dmitrievsky #:

Look at the MAE, then the graph, then the MAE, then the graph, then the MAE, then the graph, then the MAE...... then the graph.... several more iterations of shifting the focus of attention from the MAE to the graph and back again.

The error is smaller than yours. How you manage to profit from it is a mystery.

https://www.mql5.com/ru/articles/12772

I think he just learnt how to run NS yesterday :)

 
Aleksey Vyazmikin #:

Answered your questions. .

I understand a little bit about it as I myself have been puzzling over a similar task for a long time

 

So cool, you come up with an idea, implement signals (sell only), without any optimisations, throw them into the tester.


Wow, that's not a bad idea, look at the trades... everything is as it should be.



And then I decided to look at the market where the signals were tested.



And my left eye started twitching )

 
Maxim Dmitrievsky #:

The margin of error is smaller than yours. How you manage to profit from it is a mystery.

https://www.mql5.com/ru/articles/12772


Didn't really look at the chart. I'm looking at it now.
I don't believe it! It can't be because it can never be.
I'm sorry.
 
Yuriy Asaulenko #:
I didn't really look at the graph. I'm looking at it now.
I don't believe it! It can't be because it can never be.
I'm sorry.
)))))
Delete the account.)
 
mytarmailS #:

I think he just learnt how to run NS yesterday :)

Looks like my suspicions are correct
 

I went back many pages where the argument was,

I don't understand how AI can work on the market, because where AI succeeds it is a narrow circle, physiological as a rule, where there are reference points and boundaries,

pixels in/n/l/p, if you look at appearance, but what can you do with a market that has no physiological boundaries?

only in theory such developments

 
maybe my calculations backwards across all possible options is AI and I just don't know about it?
 

My understanding of MO is that you set a large series of data and they have to come to a set point, the set point is an identification, what is your MO identifying now?

like the smartest one here, in waves? (read the comments in the reviews, spinner lover)

1...347834793480348134823483348434853486348734883489349034913492...3699
New comment