Machine learning in trading: theory, models, practice and algo-trading - page 1425

 

poor thing, not enough attention... come here )))

I swear... ai prai )))

 

What about the dataset?

I have akurasi 57.3% loglos 0.688

Files:
market66.zip  3383 kb
 

The main thing is that the black box on the AOS shows approximately the same, and not as in the
(not using the forum as a pamphlet for selling the Teacher's useless rattles)))


 
Vizard_:

The main thing is that the black box and on the os about the same show, not as in the use
the main thing is that the black box works just the same, not like the one using the forum as a handout to sell useless Guru's rattles))))


What's your problem? 3% profit

you're relaming, i'm all free access in the articles, dumbass ahahahah))

a worthless lying lowlife, and a dumb one at that)
 
Vizard_:

The main thing that the black box and the AOS showed about the same, but not as in the use
(as opposed to using the AOS forum as a pamphlet for selling Teach's useless bells and whistles))))

Well, as if you're not right at all - neither you nor I posted in the public access trade monitoring, and discuss someone - how's that? only he who does nothing is not wrong? )))

Quit it or will you show me your monitoring? ;)

 

It is not in vain that they say, "You reap what you sow.

 
Petros Shatakhtsyan:

It is not in vain they say: "You reap what you sow".

There's another one on the line )) What assembly line do they use to produce you pundits?

How can we discuss anything with these "people"?) That is why the subject is dead

I wanted to have a normal conversation about ML, but it turned out that there are only jerks here
 
Maxim Dmitrievsky:

There's another one here )) what kind of assembly line do they use to produce you pundits there?

How is it possible to discuss anything with these "people"?) That is why the subject is dead

I wanted to have a normal conversation on the topic of ML, but it turned out that there are only cockamamie

If you want to discuss something normally, from what considerations once poked into my topic and got to the point that the whole topic was taken down. this is not nice.

But I'm not going to lower myself to your level.

 
Petros Shatakhtsyan:

If you want to discuss something normally, then from what considerations once stuck to my topic and got to the point that the whole topic was taken down. It's not nice.

But I'm not going to lower myself to your level.

Everyone has a different concept of beauty.

 

Can you tell me what is wrong with the neural network? I read an article on a local site about transferring a neural network from NeuroPro program to an Expert Advisor. I did everything as described and got the same result



But as soon as I go forward or backward within the next bar, as soon as I go out of the specified period, pure chaos begins, not a single sign of life, profits either immediately go to the bottom or fly off, without any signs of systematic profit increase, even a little.

Is the neural net a fit to the story? Or do I just need to change something (poke where) to make it look like a profitable one. But then what exactly needs to be changed (within the program or maybe a different program to use).

It's just extremely surprising, there is no intentional tweaking in the algorithm, as it happens in tester grails, that is, the EA does not look into the future, but the funny thing is that when you set "do not open trade if forecast less than 50 points" in the settings, then on retesting ... The only trades left are those opened right before the very news candlesticks, right in the desired direction and of the desired profit size (the entire momentum). Although, there is no trading logic in the Expert Advisor except for the set of hundreds of real numbers - weights of the neural network and the summation formula.