Machine learning in trading: theory, models, practice and algo-trading - page 1052
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
I'll do the same tomorrow
Grid(not mgua)
From top to bottom - part of inputs - pair of Fourier harmonics, lowest equi(spread 3 for euro 4zn)
After the vertical drop - oos. Undrawn otherwise long...
Grid(not mgua).
From top to bottom - part of the inputs - a pair of Fourier harmonics, the lowest equi (spread 3 for Euro 4zn)
After the vertical drop - oos. Undrawn otherwise long...
MSUA is not a panacea, but it has some serious principles which should be used, I think it is over-organization of the model (IMHO) and the author hints at it...
I generally suspect that it is not signs of selection by self-organization, but generates decision-making itself (IMHO)
On the site in the comments there is a post how the man applied a polyharmonic approximation (harmonic search) and then did a good job training the grid on this data, pre-smoothed the price with a Butterworth filter
I'll try to find this post for you, because I'm far from such matters
here's the quote.
......................................The next step was a new model: apply a low-pass filter to the closing price(I used a2nd order Butterworth filter), apply a polynomial-harmonic approximation, transform A*cos(wx)+B*sin(wx) to form M*sin(wx+f) and take M and f as secondary features.
.... And with this model I managed to build a network, which had very good generalizing properties: new data almost all correctly recognized........................
The story begins in 2006 if I'm not mistaken, you just do not suspect at what high level it's all done, and what kind of person.
http://www.kamynin.ru/
Select the rubric "trading robots". Choose the rubric "trading robots", go to the beginning, make tea and crumpets, read, look at pictures, read comments from people, the author's answers, get smarter, and not a child's ah ... ee ... ) ))
There is an opinion, that Kamynin - the same blabbermouth. Because he can't confirm his pictures with any kind of statement. And anybody can draw beautiful levels.
There is an opinion that Kamynin is a blabbermouth. Because he can't confirm his pictures with any kind of statue. And anyone can draw beautiful levels.
Well, there may be different opinions. I personally several times communicated with him, in my opinion he was a modest and very experienced guy, it was clear from his conversation that he was going in the same direction I'm going tomorrow, if you know what I mean.
There are better rattlesnakes, but that's not the point... When you train something do benchmarks.
Dakanesh is, gmdh is an ordinary network, one of.
Here it is. Came across in the wilds of the optimizer....
Here it is. Found it in the wilds of the optimizer....
Oh, that's okay.
Send me a scrapbook of the code.
let's rewrite it on mkul and we will cut the cabbage
Oh, that's okay.
Just send me a piece of paper with the code on it.
we'll copy it to mkul and then we'll chop some cabbage.
it's a pisser.....
you're not chopping anything gmdh is just an algorithm, one of.... but it has strong principles that can be used.
in R there are two packages of MGUA "GMDH", GMDH2" the first specifically for BP the second is a binary classifier, use it, but it is just a single algorithm one of...
Reshetov used mgua, did he get rich? Why don't you want to think so people?