Machine learning in trading: theory, models, practice and algo-trading - page 2734
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
from left to right or right to left.
So you even know Russian so well that you write as luck would have it?
Who are you, monster?So you even know Russian so well that you write as luck would have it?
what are you, monsterptsc....
I don't give a damn about empty words, no matter how well written they are.
Especially since it's been going on for 2700 pages.
and all to no avail.
link: ; ))))
but basically, if it's up now, the next bar is down.
If it were like that, even if it was approximately like that, there would be no topic about MO :-)
and there are micro-trends and seasonals and reversals and they react to tick volume and all sorts of things. And they do not differ in principle from ordinary bars, black and white in statistics. Exactly the same, the replacement does not simplify the task at all
If it were so, even if it was even approximately so, there would be no topic about the MoD :-)
and there are micro-trends and seasonal trends and reversals and they react to tick volume and all sorts of other things. And they do not differ in principle from ordinary bars, black and white in statistics. Exactly the same, the replacement does not simplify the task at all
Yes, of course.
there are no fish there.
absolutely not.
;)
There is no point in looking at the old model, it doesn't capture market changes.....
I disagree - a significant change in the leaf activation rate is indicative of missing conditions in the sample, and therefore a change in the sample.
I did this to identify predictors suitable for training on the whole population, I wrote here earlier about the positive results of the experiment. And so, they will always float within their group. You can make a script in R for calculations for my sample - I will run it for the sake of the experiment.
The experiment should reveal the optimal sample size.
I disagree - a significant change in leaf activation rate indicates a lack of conditions in the sample, and therefore a change in the sample.
You can make a script in R for calculations for my sample - I'll run it for the sake of experimentation.
If you start to examine quotes as a time series, you may notice some peculiarities that are not found in other time series. Perhaps there are patterns in these features. And yes, not everything can be pulled out by autoregression and classification directly using lag features, but with the addition of ingenuity you can
Personally, I abhor the original idea of quotes as a time series. If I formalise my idea of them mathematically, they are piecewise constant functions of time (continuous on the right). Moreover, the area of values can be of very different nature - e.g. numbers, vectors, state of the glass, etc. In addition to the prices themselves, there is other necessary information, which can be represented by the same functions (session state, news, etc.), and the area of values here can also be very diverse.
But meaningful computational work with continuous time functions is practically impossible, so some discretisation is always done. It can be done very differently and unanimity is hardly achievable in principle.
Personally, I dislike the original idea of quotes as a time series. If I formalise my idea of them mathematically, they are piecewise constant functions of time (continuous on the right). Moreover, the area of values can be of very different nature - e.g. numbers, vectors, state of the glass, etc. In addition to prices, there is other necessary information, which can be represented by the same functions (session state, news, etc.), and the area of values here can also be very diverse.
Why do we need a "representation"? What is the purpose of "representations"?
If the purpose is philosophical, there are no questions.
But in financial markets there are only two purposes: to predict value and to predict direction (sign).
If "representation" is for this purpose, then what influence, how related, what predictive power do all these "representations" have for the above purposes?
What is the purpose of "representations"? What is the purpose of "representations"?
If it is philosophical, there is no question.
But in financial markets there are only two purposes: to predict the value and to predict the direction (sign).
If "representation" is for this purpose, what influence, how related, what predictive power do all these "representations" have?
To give the participants of the discussion a better understanding of the ideas, the representations are very different for everyone here, even on the initial concepts. On representations depends the closeness of models of objects to the objects themselves.