Machine learning in trading: theory, models, practice and algo-trading - page 2557
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
the sloping line is non-stationary, and it's all about time series.
stop talking nonsense, where did you weirdos come from again? :D it's only worth warming up the topic.
Sorry. Go on rocking like you've been doing for the last SEVEN years...
then all is futile )
why?
it's just that we don't look for one correct cycle (sinusoid) which doesn't exist
but several simple cycles (sinusoids) the sum of which will create our complex non-sinusoidal cycle (complex from the word add)
Sorry. Keep kamlalaing like you have been doing for the last SEVEN years...
I didn't ask for advice.
I didn't ask for advice.
This is not advice.
And this is not advice.
Opinion is not interesting either, your personality even less so
Well there in the second part is interesting, in the end about time series and his experience with it. The rest is up to everyone
At one time I took this course on intuition.
There are different kinds of non-stationarity. Only those that are algorithmically reducible to stationarity are available for study. For example, econometrics uses detrending and transition to differences. Another example would be HMM.
Regarding prices it is impossible (due to lack of data) to make a definite conclusion about the type of nonstationarity and whether there is (and what, if any) algorithm for the reduction to stationarity.
Alexei, do you have a good understanding of hmm?
At one time I took this course on intuition.
There are different kinds of non-stationarity. Only those that are algorithmically reducible to stationarity are available for study. For example, in econometrics, detrending and transition to differences are used. Another example would be HMM.
Regarding prices - in principle it is impossible (due to lack of data) to make a definite conclusion about the type of non-stationarity and whether there is (and what, if any) algorithm for reducing to stationarity.
Why do we need to detrend? It's like we need to look for trends. We should rather de-trend.)
I couldn't have said it better.
Well done, but what to do?
Globally, I don't know. Locally - I try to choose predictors that are as unsteady as possible. From my observations, all derivatives of the zigzag may be based on the prices of one asset.
Then everything is fuzzy ) and it is clear that the quotes are non-stationary, and it is cycles we are looking for.
There seems to be some cyclicality in the sense of repeatability (but not periodicity). Sometimes there seems to be some inertia. This gives me some hope.)