Machine learning in trading: theory, models, practice and algo-trading - page 1880

 
Evgeny Dyuka:
ay, administrator, this is not a rhetorical question, please answer,
for example: "according to our rules it is forbidden..."
to know
... it looks like the administrator himself is in the excruciating process of creating a neural network ))
 
Evgeny Dyuka:
... it looks like the administrator himself is in the excruciating process of creating a neural network ))

it looks like you're tired of shoving your comment product in here

next time you'll just get banned silently

 
Maxim Dmitrievsky:

it looks like you've had it up to here with your comment product

Next time they'll just ban you silently.

here's the adminstrator ))
and it's high time I was banned.

by the way, all those from this thread I gave unlimited
+ thanks for the "comm. product" so it's not a "fake", but something real.
 
Evgeny Dyuka:
here is the administrator ))
and I should have been banned long ago.

By the way, all those from this thread I gave unlimited
+ thanks for the "comment product" means all the same not a "fake", and something real.

ask, they'll cut it out.

 
Maxim Dmitrievsky:

So normalize the 2nd one to the 0 bar, then it won't be 0.5

There is a linear change there, i.e. the curves lie on 1 line. So the correlation between clocks tends to one. Check it... use your brain

3 is not enough - make it 500 :) just give me a reason why

Honestly, I don't even know what you mean)

I'm not planning to do anything, I'd rather wait until you do the test yourself))

 
mytarmailS:

Honestly, I don't even know what you mean.)

I don't plan to do anything, I'd rather wait for you to test it yourself))

cunning

 
Evgeny Dyuka:

Hi Zhenya! Anything new to read on the hubra?

 
mytarmailS:

Hi Zhenya, is there anything new to read on the hubra?

Hello, I tried to write two times already, but the muse does not come, and there are no breakthroughs yet, I stand still...
 
Evgeny Dyuka:
hello, I've already tried to write two times, but the muse doesn't come, and there are no breakthroughs yet, I'm stomping in place...

What are your problems? May be I can help you with words of kindness)

 
mytarmailS:

What's your problem? Maybe I can help with a kind word)

The problem is that the data preparation scheme seems to have exhausted itself, more than 65-66% correct answers do not get squeezed out, and should be more. I am looking for a way to break through this wall.