Machine learning in trading: theory, models, practice and algo-trading - page 1345
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
By the way, has anyone seen Trickster? It makes me want to debate with him..... Yes, it was a time.... We are not We!!! :-)
The sorcerer ran to the rescue, overtaken by angry investors Aliosha... He will be back soon.
The notion of a spectrum is defined only for a stationary process. Price is not, if only because of the growth of dispersion over time.
What nonsense you are saying...
Apparently, the concept of spectrum is left unexplored for you, foggy.What nonsense you're talking...
Apparently, the concept of spectrum is left undisclosed to you, foggy.Oleg, do you want to talk about spectrum?
How does it apply to market price formation?
1) Oleg, do you want to talk about spectrum?
2) How does this apply to market price formation?
1) I don't want to talk to you about anything. Your knowledge "about the spectrum" is limited to this picture.
2) Your question just confirms your lack of knowledge and understanding of the "spectrum".
1) I don't want to talk to you about anything. Your knowledge of the spectrum is limited to this picture.
2) This question of yours only confirms your lack of knowledge and understanding "about the spectrum".
I even have a prism in my box, so there is some practical knowledge "about the spectrum"
Would you like to discuss this?
I even have a prism in my box, so there is some practical knowledge "about the spectrum"
You want to talk about it?
Send you in...
Should I send you...
What, another prism for you?
So I if anything, I can give mine, already played.
Where to, to get another prism for you?
I can give you mine if you want, I've already played with it.
You must think you're pretty witty.
Take a second look at yourself, you look pathetic...
Now about data preparation for training.
We obtain a series from the random number generator (RNG) and transform it into a form close to the market one. Such series has an unlimited spectrum and it is not real to predict its values.
2. we pass the series through low pass filter (LPF). You have received a random series with a limited spectrum and possibility to predict for n-counts ahead, however it is not very similar to the market series.
3. We generate series with M=0 by the RNG and add it to the series after the LPF, after some tambourine play. We again obtain a series close to the market one. We will use this series for training.
4. As the target function we take the series in step 2 passed through the LPF and shifted by N samples backward that corresponds to the forecast for N samples forward.
Then we feed input and target series to NS, train and check training results. Then repeat steps 1-4, fed series in step 3 to the NS and compare the output of the NS with a series shifted by N samples in step 4.
That's it. No miracles. You can do it all without the NS. What surprised me was that the NS did it in seconds, and in just 24 loop of training. And that's with a lot of noise, you can't even see the low frequency component there. That's amazing.
Why didn't it work with the market BP? Any LPF has significant delays, and its curve is shifted to the right relative to BP. That is, we have a delayed LF signal at every point in the series, and thus the prediction interval is larger than allowed, and the prediction becomes unrealistic. We can't even build a real target for training.
Thanks for detailed explanation. As far as I understand, in fact NS in such a scheme is used as a noise filter. I.e. a muve is built using pseudo-marketquotes, then noise with constant variance and expected payoff is added and the same muve shifted by a forecast interval is used as a target one for training. As a result, NS learns to remove noise and forecast the moove by regression. Right?
What nonsense you speak...
Apparently, the concept of spectrum has remained unrevealed to you, foggy.Learn the theorist not from Cicero's speeches, but from textbooks. Look, for example, Korolyuk recommended by you.