Dependency statistics in quotes (information theory, correlation and other feature selection methods) - page 59

 
VNG:

Here's a screen with a consistent pattern repeatability. There are a lot of smart, savvy programmers here. Try to formalise it. I think you won't succeed.

The task is as follows.

Based on the first two movements of the impulse-correction calculate the probability of formation of the third part of the impulse.

That will be one move. On the screenshot, the run length and arrival time to the end point of the orange and green impulses.

Ahh, I see which step you want to predict.

I have a more modest task - one bar of the current TF.

 
VNG: There is no gut feeling here, the rules are ridiculously simple.
The rules for the pattern? Are there multiple TFs or different zig-zag steps?
 
One bar cannot be predicted.
 
Mathemat:

Again I don't get it - or are you holding on to your beliefs?

There's no algorithm laid out here for how to eat it. But that doesn't mean it can't be invented.

The trick is that and TAdv is on the other side of good and evil, but it works if you believe ..

Why hold on.... It's just that I've got an awful lot of known methods in front of me that I'll never be able to master.

And about the chip. A man takes a tool (chip) and for some unknown reason knows how to use it to enrich yourself. The problem is that you can spend years and then find out that you either can't learn this trick (not given), or it was a fake. And too bad that in the beginning there was proof that this is not a tool, and do not know what. But greed overcame thoughts of chiromancy.

So I say:

(a) what is the error of prediction?

(b) can this prediction error be trusted?

(c) why will the answers to the first two questions be valid in the future?

No answer to these questions - everyone, off the screw and gazing with delight at a depot with 200 times growth in three months.

 
DmitriyN: One bar cannot be predicted.
Can you justify it?
 
faa1947:
"A stochastic component which cannot be measured at all - the mood of the crowd. For most of the time, the main characteristic of this component is random wandering with drift."

What is meant by a crowd?

Is there a justification for the influence of the crowd on a quote, or that there is a crowd influence in a quote? In every quotation or only in some?

 
Mathemat:
Justify?
Don't pester the man. The forecast error for each successive bar adds up. It is very difficult to get an acceptable forecast error even for one bar.
 
faa1947:

Why am I hanging on to.... It's just that I have a huge number of known working methods in front of me that I'll never be able to master.

And about the chip. A person takes a tool (a chip) and for some unknown reason knows how to use it to enrich himself. The problem is that you can spend years and then find out that you either can't learn this trick (not given), or it was a fake. And too bad that in the beginning there was proof that this is not a tool, and do not know what. But greed overcame thoughts of chiromancy.

So I say:

(a) what is the error of prediction?

(b) can this prediction error be trusted?

(c) why will the answers to the first two questions be valid in the future?

No answer to these questions - everyone, off the screw and gazing with delight at a depot with 200 times growth in three months.

It's hard to explain something new to you, you're stiff. That's a fact, I don't give a damn about the rest. Don't look at my charts if they bother you.
 
VNG:

What's the gut feeling? What's the hesitation? The stability of the pattern. Well, you can do it yourself on history, and you'll see. There's no flair, the rules are ridiculously simple.


If you can build it, but you can't formulate the rules, then it's a gut feeling.)

 
IgorM:
rules for building a pattern? are there multiple TFs or different zig-zag steps used?

The TF is not involved at all. The constructions at the price extremums are used. The steps are set by the market. The rules for drawing and transitions are given on Onyx. Implicit price and time discretization with variable steps.