Machine learning in trading: theory, models, practice and algo-trading - page 1040
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
Could you elaborate on the scripts?
I have no problem combining the components of an R program into a single whole.
One call to R in the OnInit section, and one call to OnTick for a signal that produces a dozen or so functions written in R. Inside these functions are calls to functions from R packages, including computationally complex ones, i.e. which call functions written in C++ or Fortran, I don't know exactly. All this diversity is not visible from the EA, changes in R texts do not change anything in the EA....
What is my problem? And how would this problem, which I don't see, be solved in Python?
I'm not quite sure what the actual question is.
An article on scripting languages for general reference -https://ru.wikipedia.org/wiki/Сценарный_язык The article is somewhat outdated, but gives some insight.
R is also no more than a highly specialized for its environment scripting language designed to manipulate its own packages specialized for R environment.
Mm-hmm....
Apparently, having finally lost their minds, the members of this thread decided to take a break...
That's right!
However, I will still allow myself a question:
At Kolmogorov, to predict the next NE value, two conditions are necessary:
1. Expectation of NE must be =0.
Two things satisfy this criterion:
a) returns (first differences, increments) of price
b) sum of increments in the sliding window
Okay. Returns have been knocked up and down - no fish. The sum of increments has not yet been calculated, right?
2. ACF in the sliding window must be:
a periodic function. Right?
Has anyone tried to plot the frequency distribution of this function? What should it be to make money flow unrestrainedly into our pockets?
Tired of struggling with forex and from trying to enter the top of Forbes, we here cheerfully decided that dumbing down is not the worst style of existence :))
Tired of struggling with forex and from trying to make it to the top of Forbes, we here cheerfully decided that dumbing down is not the worst style of existence :))
:)) I agree, Max. But, for truth's sake, I do, on occasion, revisit the happy past... Dreams of the Grail are indestructible... It's time to write a poem :)))
:)) I agree, Max. But, for truth's sake, sometimes I do go back to my happy past... Dreams of the Grail are indestructible. It's time to write a poem :)))
Regarding ACF - I keep sticking to my opinion, that returns have to be reversed after some point, and to look for the best point, where there is a clear periodicity in ACF on both chunks. Then predict something based on the past inverted returnees. But so far, of course, I haven't done it myself :)
Errors, by the way, will also be quite significant, but forecasting will not be as random as with all these autoregressions and garches. + You have to modify the model specifically for different situations.Regarding the ACF - I continue to stick to the opinion that returns should be inverted mirror-like after a certain point, and look for the best point where there is a clear periodicity in the acf on both pieces. Then predict something based on the past inverted returnees. But so far, of course, I haven't done it myself :)
Let me reassure you a little - the ACF in Erlang flows takes on a periodic appearance when the order of the flow is increased.
Only(!) in Erlang flows and nothing else. Working with OHLC on bars M1, M5, etc. does not give this effect.
But, in view of the lowest level of the participants of this forum, the utter stupidity in the eyes - this problem will be solved for a long time yet... IMHO.
We are waiting, as usual, Koldun and Aleshenka. They will come at the right time. I believe in it.
A little encouragement - the ACF in Erlang flows takes on a periodic appearance when the order of the flow is increased.
This is clear to the hedgehog. But in spite of this, the result will be zero on the deposit.
Only(!) in Erlang flows and nothing else. Working with OHLC on bars M1, M5, etc. does not give that effect.
Forgive me, Alexander, but you are talking such a crazy talk that even I cannot stand it).
This is exactly the case described in the literature - woe from the mind) IMHO.
It is clear to the hedgehog. But in spite of this, the result will be zero on the deposit.
Forgive me, Alexander, but you are so wildly ridiculous that even I could not stand it).
This is exactly the case described in the literature - woe from mind) IMHO.
No, well, I could be wrong, Dmitry - I just can not compare everything. I just saw the periodicity of the ACF of EURJPY in the Erlang of the 30th order and got happy... I haven`t seen it before...
Regarding the ACF - I continue to stick to the opinion that returns should be inverted mirror-like after a certain point, and look for the best point where there is a clear periodicity in the acf on both pieces. Then predict something based on the past inverted returnees. But so far, of course, I haven't done it myself :)
The errors, by the way, will also be quite significant, but prediction will not be so random as with all these autoregressions and garbage. + There you have to make a model specifically for different situationsBright idea, which says only that you don't have the slightest idea about ACF.
A bright idea that only shows that you don't have the faintest idea about ACF.
go on...