Machine learning in trading: theory, models, practice and algo-trading - page 2141
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
Vladimir, do you know what sickness ZZ from TTR package
Sometimes he draws such inadequacies
пример zz <- TTR::ZigZag(HL = cbind(d$X.HIGH.,d$X.LOW.) ,change = 0.0009,percent = F)
And in general, the more I look at him, the more inadequate he seems to meThis and in MT with zigzag
Is it normal?
Is this normal for you?
No, of course not
Then why is this happening?
then why does this happen?
Well apparently not all cases are taken into account in the algorithm, what else can you say?
Regarding the TF invariant normalization for the model ...
we take the series, we single out the important break points
we leave only the extrema points, delete the rest
normalize
now we take the distances between the breakpoints in the first series, create a new series from them and normalize too
thereby we obtain the normalized series, both by scales (amplitudes) and by time (frequencies)
All that is needed is to keep the number of extrema in the pattern even, everything else is normalized.
Thus, you can feed the model with data, no matter how many minutes or weeks, it will see it as the same thing, it will be invariant to the TF.
You may train one model for all TFs at once
=============================================
For those who haven't understood what it is and what it is for
For the model it will be one and the same pattern, because it is one and the same pattern
Regarding the TF invariant normalization for the model ...
we take the series, we single out the important break points
we leave only the extrema points, delete the rest
normalize
now we take the distances between the breakpoints in the first series, create a new series from them and normalize too
thereby we obtain the normalized series, both by scales (amplitudes) and by time (frequencies)
All that is needed is to keep the number of extrema in the pattern even, everything else is normalized.
Thus, you can feed the model with data, no matter how many minutes or weeks, it will see it as the same thing, it will be invariant to the TF.
You may train one model for all TFs at once
=============================================
For those who haven't understood what it is and what it is for
For the model it will be one and the same pattern, because it is one and the same pattern
does not work
it's not working
What's not working? Normalization? Are you sleep-deprived or what?)
Run this ZZ in the NS
it should be done in the sliding window, but n extrema, not all of them, that's the first thing
second, all that I have written was done to predict a trend line, and not just for fun...
All those transformations were done for a certain task.