Machine learning in trading: theory, models, practice and algo-trading - page 997

New comment
 
Aleksey Nikolayev:

Therefore, the article (about stationary random sequences) is not of much help to us.

The article won't help much, but it won't be superfluous. But understanding of the market as a random process may help. But not 100%.
 
Maxim Dmitrievsky:
I'm not judging anyone, and I communicate with the shitheads as it should be, it would be strange if there was a different reaction to you jokers. Get into a pile and start defending yourselves all together now, it's the last thing you can do. Don't you wonder why others respond normally?
Defend myself from who? You're not confused, are you?
Go see a psychiatrist after all. You never know.
 
Yuriy Asaulenko:
Protect yourself from whom? Aren't you confused?
Go see a psychiatrist after all. You never know.
It's not even interesting to answer you, nonsense, go to the stall with the others like you.
 
Alyosha:

Hmmm... is there any progress? But no... I do not believe ...

Don't shoot the pianist, he plays as he knows how.
 
Yuriy Asaulenko:
The article won't help much, but it won't be superfluous. On the other hand, understanding the market as a random process may help. But not 100%.

I agree that:

Understanding the market as a random process - can help

Understanding what a stationary random process is - can't hurt

But:

Understanding the market as a stationary random process - would rather do harm

 
Aleksey Nikolayev:

Understanding the market as a stationary random process is more likely to hurt

It won't do any harm either.) If we exclude the trend component, the market is stationary. It's easy to check it at least in Excel.
The kind of distribution is another song.)
 
A flat came, the branch came alive...
 
Yuriy Asaulenko:
No harm done either.) If we exclude the trend component, the market is quite stationary. It's easy to check it at least in Excel.
The type of distribution is another song.))

Excel is a serious program - it can remove everything from past prices and make the market not only stationary, but even constant)

In case of a stationary process the song is much more cheerful - sample distribution converges to the real one with the increase of sample volume, and in case of non-stationary one it (most probably) does not converge to anything.

 
Aleksey Nikolayev:

Excel is a serious program - you can remove everything from past prices and make the market not only stationary, but even constant)

In case of a stationary process the story is much more cheerful - the sampling distribution converges to the real one with the growth of the sample volume, and in case of non-stationary one it does not (most likely) converge to anything.

There is an opinion that with some "thinning" of initial BP it will be possible to get a process closest to the stationary one.

 
Alexander_K2:

There is an opinion that with some "thinning" of the initial BP it will be possible to get the process as close to stationary as possible.

Strange opinion.) Why should it be?
1...99099199299399499599699799899910001001100210031004...3699
New comment