Machine learning in trading: theory, models, practice and algo-trading - page 1087
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
Yes yes, that's where I should have started...
1) I tried with "DTW" but it's a very heavy design, I never finished the experiment, because I couldn't think out some conceptual things in the algorithm...
2) Maybe we should break the BP into fourier harmonics? there are three parameters: amplitude, frequency and phase. then we can translate these parameters not in a numerical form but in a proportional one, for example
We have amplitude (amplitude range of motion), take for example the first harmonic and the fifth one, the amplitude of the first one is 100p and of the fifth one 10p. We divide one by another and obtain a universal characteristic - proportional.
Those are not 100 and 10 amplitudes, but just the knowledge that the first amplitude of the first harmonic is 10 times greater than the fifth, and this is a universal measure that will be repeated in the future and is essentially objective. But of course it would be better if some experienced spetrator expressed his opinion on this matter.
What's going on with your networks? If you do not want to help me to transfer my indicator to MetaTrader, you may even write a robot there and get an indicator + new knowledge on how to use networks in trading, a working knowledge
what is DTW?
There are quite clear and described approaches of using MO for time series, I prefer not to come up with all that crap... moreover I don't understand why we need Fourier, in the light of what I've just said about market cycles. You can do the analog of Fourier without bpf.
I haven't done anything, I just read the literature. Or is everyone here used to do all sorts of c... without knowing what's going on? :)
I thought that Perervenko started to rewrite... I don't know how to do it, it takes a long time to figure it out.
The most sacred thoughts on the TC are not disclosed, or only after it is proved that it does not work :) then you can somewhat relieve the publicans, a kind word to their intellectual image
About the levels have already been proved, if there are any illusions, it is possible to destroy them ... from 1 minute to a day to refute them. Most will take no more than 5 minutes purely theoretically
Yes yes, that's where I should have started...
1) I tried with "DTW" but it's a very heavy design, I never finished the experiment, because I couldn't think out some conceptual things in the algorithm...
2) Maybe we should break the BP into fourier harmonics? there are three parameters: amplitude, frequency and phase. then we can translate these parameters not in a numerical form but in a proportional one, for example
We have amplitude (amplitude range of motion), take for example the first harmonic and the fifth one, the amplitude of the first one is 100p and of the fifth one 10p. We divide one by another and obtain a universal characteristic - proportional.
Those are not 100 and 10 amplitudes, but just the knowledge that the first amplitude of the first harmonic is 10 times greater than the fifth, and this is a universal measure that will be repeated in the future and is essentially objective. But of course it would be better if some experienced spetralshchik expressed his opinion on this subject.
What's going on with your networks? If you want to trade with them, they may be of different types, e.g., wholesale or retail, for example, wholesale or retail.
tantrum...
There are frequencies rather than amplitudes, a frequency-phase spectrum, and there is an indistinguishable marginal effect after the opf
what is DTW?
I think it is a discrete Fourier transform
It won't work with Fourier, search through the forum works fine, there were many discussions about Fourier and why it's not suitable
I think it is a discrete Fourier transform
It won't work with Fourier, search the forum works fine, there was a lot of discussion about Fourier and why it doesn't fit
Yes, and it's done just fine through AR. Fourier transform is not used in econometrics at all as I think.
What is DTW?
There are quite intelligible and described approaches of using MO for time series, I prefer not to make up any bullshit... especially I don't understand why we need Fourier, in the light of all mentioned above about market cycles. You can do the analog of Fourier without bpf.
I haven't done anything, I just read the literature. Or is everyone here used to do all sorts of c... without knowing what's going on? :)
I thought that Perervenko started to rewrite... I don't know how to do it, it takes a long time to figure it out.
The most sacred thoughts on the TC are not disclosed, or only after it is proved that it does not work :) then you can somewhat relieve the publicans, a kind word to their intellectual image
About the levels have already been proved, if there are any illusions, it is possible to destroy them ... from 1 minute to a day to refute them. Most will take no more than 5 minutes purely theoretically
DTW this
https://ru.wikipedia.org/wiki/%D0%90%D0%BB%D0%B3%D0%BE%D1%80%D0%B8%D1%82%D0%BC_%D0%B4%D0%B8%D0%BD%D0%B0%D0%BC%D0%B8%D1%87%D0%B5%D1%81%D0%BA%D0%BE%D0%B9_%D1%82%D1%80%D0%B0%D0%BD%D1%81%D1%84%D0%BE%D1%80%D0%BC%D0%B0%D1%86%D0%B8%D0%B8_%D0%B2%D1%80%D0%B5%D0%BC%D0%B5%D0%BD%D0%BD%D0%BE%D0%B9_%D1%88%D0%BA%D0%B0%D0%BB%D1%8B
that was about fractality.
i don't know how to do it, it takes too much time to analyze it, i know how to connect the bridge and make the graphical output in mt4
tinny...
there are frequencies and not amplitudes, frequency-phase spectrum, and after the opf the edge effect is indistinguishable
there are amplitudes and phases and frequencies
I think it's a discrete Fourier transform
No way to do it with Fourier, search the forum works fine, a lot of discussion was about Fourier and why it doesn't fit
Yes, and it's done just fine through AR. Fourier is not used in econometrics at all in my opinion
you don't understand the thought ... it's all about fractality too, I was describing the idea of how to find the same pattern on a chart, even though it can be and is of different sizes and spreads
there are amplitudes and phases and frequencies
you do not understand the thought ... it's all about fractality, I was describing the idea of how to find the same pattern on the chart, while it can be and is of different sizes and scales
I should have written it that way, I read about speech recognition on hobrehabre and there was an algorithm mentioned by you
https://habr.com/post/226143/you do not understand the thought ... it's all about fractality, I was describing the idea of how to find the same pattern on the chart, while it can be and is of different sizes and sweeps
it's easier to look in the rest of the patterns
It's easier to look in the rest of the models
how is it?
how's that?
it's a creative assignment to think about how it is )