Machine learning in trading: theory, models, practice and algo-trading - page 2666

New comment
 
mytarmailS #:
It is not a fact that it will fall, maybe at this very moment the euro was ahead of the global trend.
And what is a global trend? Where are the statistics that it even exists and works, and even if it works, where is the guarantee that at the moment when you saw that the GT is down it will not go up, as it always happens...?

Well, I'm very sceptical on this subject and I've justified my position.
When the market goes up or down on average. Not just one stock, but the whole market.
 
Maxim Dmitrievsky #:
When the market is up or down on average. Not just one stock, but the whole market.
I get it, but that doesn't make the trend predictable.
 
mytarmailS #:
I get it, but it doesn't make the trend predictable.

Yeah.)

 
Maxim Dmitrievsky #:

Yeah )

That's why we're going back to the beginning of the conversation, it's the same as looking at mashka)) same lag, same problems
 
mytarmailS #:
That's why we're going back to the beginning of the conversation, it's the same as looking at a car)) the same lag, the same problems.

then we move on to option 2 (although I don't completely agree with the first one, there is a point there).

 
Maxim Dmitrievsky #:

then we move on to option 2 (although I don't completely agree with the first one, there is a point there)

And what is option 2?

 
Maxim Dmitrievsky #:

And if the Eurobucks is rising and other correlated pairs are falling. You can't filter it out like that, and logically, you should prohibit trading at that moment or make a corresponding markup. Your chart won't show that. For example, the Global is trending down, and the Eurobucks is rising in the moment, but then it will also fall. You will get additional markings that do not correlate with the trend, scattered by noise. But this is just philosophy.

Anyway, I was not lazy, I made a general trend for 28 pairs via PCA, I didn't do anything with correlations, I didn't flip pairs, I was lazy...

Here are all the components together, the most common trend, the price of the euro on top, the trend on the bottom.

See for yourself.

=======

You can also look at individual components, filter them, etc.


 
mytarmailS #:

So, I was not lazy. I made a general trend for 28 pairs via PCA, I didn't do anything with correlations, I didn't flip pairs, I was lazy.

Here are all the components together, the most common trend, the price of the euro is on the top, the trend is on the bottom.

you see for yourself.

=======

you can also look at individual components, filter, etc.


You probably don't need all of them, just the ones that correlate. I've already done it. The results on the forward are slightly better.
 
mytarmailS #:
That's why we're going back to the beginning of the conversation, it's the same as looking at the mashka)) same lag, same problems.

You're right! "Looking at the mashka" is of little use....

I don't understand another thing... Why do you stick to the oldest trend indicator?...?

There are a lot of other trend indicators... Have you tried to look for them?...?

 
Serqey Nikitin #:

You're right! "Looking at the mashka" is of little use.....

I don't understand another thing... Why do you rely on the oldest indicator to determine the trend?...?

There are a lot of other trend indicators... Have you tried to look for them?...

What's the oldest indicator I'm stuck with?
1...265926602661266226632664266526662667266826692670267126722673...3699
New comment