Machine learning in trading: theory, models, practice and algo-trading - page 2013

[Renat Akhtyamov]

Maxim Dmitrievsky:
Don't write that way, there won't be much ponapisnon. That's it, go away, do not beep my phone

Let it beep, I'm writing - read.

Read carefully, it is useful.

it's useful to look at it from the outside.

do not waste time, machine learning will never pay off.

first post of the thread: 2016.05.2614 :32

4 years, no results.

;)

[mytarmailS]

Renat Akhtyamov:

Akhahaha, what is it again? )))

PSHNH!!! cute)))

[Evgeny Dyuka]

https://www.mql5.com/ru/blogs/post/740138

[Aleksey Vyazmikin]

Evgeny Dyuka:
https://www.mql5.com/ru/blogs/post/740138

The goal is to create a database of tools where your network works?

[Evgeny Dyuka]

Aleksey Vyazmikin:

The goal is to create a database of tools where your network works?

there is no purpose, just so-so...

[Forester]

Evgeny Dyuka:
https://www.mql5.com/ru/blogs/post/740138

1) How do you do the markup, the target? For example: if 100 pt went up, it means the trend is up, if 100 pt goes down, then the trend is down?
2) I also get packs of unidirectional signals from the network. Sometimes I get 100 or even 200 losses in a row. I have only one way out - to trade with microscopic lots, like 0,5% of deposit.
Who has ideas how to avoid trading hundreds of signals in a row?
Trade the first one and then not trade until the open one closes? I think this is not the best option.

[Evgeny Dyuka]

elibrarius:

1) How do you do the markup, target? For example: went up 100 pt, so the trend is up, if down 100 pt, then the trend is down?
2) I also get a bunch of unidirectional signals from the network. Sometimes I get 100 or even 200 losses in a row. I have only one way out - to trade with microscopic lots, like 0,5% of deposit.
Who has ideas how to avoid trading hundreds of signals in a row?
Trade the first one and then not trade until the open one closes? I think this is not the best option.

1) I do not disclose how the data is prepared, sorry

2) Not for trading at all, it is just a research, now this is the simplest version, but there are many improvements, I will tell you about them later.

[Forester]

This is a question for everyone:
I also get batches of unidirectional signals from the network. It's similar to this one.

Sometimes I get 100 or even 200 losses in a row. There is only one way out - to trade with microscopic lots, like 0.5% of the deposit.
Who has ideas how to avoid trading hundreds of signals in a row?
Trade the first one and then not trade until the open one closes? I think it is not the best option.

What are the options?

[mytarmailS]

This is a question for everyone:
I also get batches of unidirectional signals from the network. It's similar to this one.

Sometimes I get 100 or even 200 losses in a row. There is only one way out - to trade with microscopic lots, like 0.5% of the deposit.
Who has ideas how to avoid trading hundreds of signals in a row?
Trade the first one and then not trade until the open one closes? I think it is not the best option.

What are the variants?

1) change the target

2) sum / separate signals

[Evgeny Dyuka]

Elibrarius:

This is a question for everyone:
I also get batches of unidirectional signals from the network. It's similar to this one.

Sometimes I get 100 or even 200 losses in a row. There is only one way out - to trade with microscopic lots, like 0.5% of the deposit.
Who has ideas how to avoid trading hundreds of signals in a row?
Trade the first one and then not trade until the open one closes? I think it is not the best option.

What other ideas do you have?

It is just necessary to poll not one model, but dozens of models at once and process their answers correctly. We get a collective opinion and it becomes very adequate. Later I will post the code how to do it.