The market is a controlled dynamic system. - page 44

 
gpwr:

I actually looked at this thread several times and did not understand what trading system we are talking about here. I don't have time to re-read the whole thread from the beginning. Can you briefly describe this system or point me to the post that describes it. What currency pair does the tractor use? What is the timeframe? Can you sketch the trades on the price chart?

if there's no time....

The system works on any instrument.

 
Tantrik:
aren't you freaking out? but here AVTAR is giving out prizes to the most ugly - http://www.procapital.ru/showthread.php?t=41961

Right ;) And you can get a prize if you guess ;)

But the thing is, people there have known each other for a long time and have an idea of the different possibilities. I mean, it's not really a guessing game. You know?

 
avtomat:

Right ;) And you can get a prize if you guess ;)

But the thing is, people there have known each other for a long time and have an idea of the different possibilities. I mean, it's not really a guessing game. You know?

It's kind of creepy - I'm out of here.
 
Tantrik:
I feel like I'm getting out of here.

that's right -- go... there's nothing for you to do here... you don't know how to do anything else but slop...

 
avtomat:

if there's no time....

The system works on all instruments.


Thank you. I'll get into the act.
 
avtomat:

that's right -- go... there's nothing for you to do here... you don't know how to do anything else...

"You got a khohol, the Jew cried" (Ukrainian proverb), gathered the girls and gives them a 100-dollar bonuses (smiles, cult of personality). Open a PAMM - then you'll say you're "cool".
 
Tantrik:
The "Khohol was born and the Jew cried" (Ukrainian proverb), gathered up the girls and rubbed in 100 quid' worth of bonuses (smiles, cult of personality). Open a PAMM - then you'll say you're "cool".
I'll dance to your tune ;))))))))))))))))
 
gpwr:

Thank you. (chuckles) I'll look into it.


First question:

In any system where only the output (the noisy signal) is observed, the signal cannot be isolated unless some assumption is made about the noise, the signal and the system. For example, in a Kalman filter, noise is assumed to be Gaussian and the system is linear. What are your assumptions about the system and the noise?

 
gpwr:


First question:

In any system where only the output (the noisy signal) is observed, the signal cannot be isolated unless some assumption is made about the noise, the signal and the system. For example, in a Kalman filter, noise is assumed to be Gaussian and the system is linear. What are your assumptions about the system and the noise?

Take the time to read this, though, and read it first.
 
avtomat:
Take the time to do that though, and read it first.


I've been reading. The beginning of the thread was interesting. I was loaded up with popcorn, sat down in a soft armchair and got a pen and paper ready. I thought I was going to take notes on clever ideas and understand every detail. But then I was quickly disappointed. Nothing is explained apart from the introduction. Why does one need the X signal? How to trade by it? By the intersection of X and Y or what? How are the W(s) structures selected? Is it a breakout and an error? What is the market sense of X and W?

Here's a pressing problem from my field. We have a radio receiver. It receives a useful signal X with noise F. We know in advance that the signal spectrum is at [f0-b,f0+b]. Our task is to decode the signal X. All this is similar to the problem posed here of finding the control signal X in the market quotes. The radio receiver problem can be simplified by shifting the signal spectrum by a mixer to [0,b] and then filtering it by a low-pass filter with cut-off frequency b. The result is a signal + noise in the frequency range [0,b]. Here is an unsolved problem: how to separate the signal from the noise in this range? The greater the noise, the greater the signal decoding error. As I understand it, you are trying to find the signal X

- without knowing its maximum frequency b

- without knowing its statistical characteristics

- without making any assumptions about the distribution of the noise.

How is that possible? And if it is possible, then let's patent a radio receiver in which the signal is separated from the noise without knowing anything about both. Why do you think X is the control signal and not F noise. What are your criteria for the signal?

Reason: