Machine learning in trading: theory, models, practice and algo-trading - page 1765
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
1. There may be predictors associated with ZZ. How do you determine ZZ period? Does the result change as the ZZ period changes?
It is understandable - the tendency is more likely to continue than to end... Do the predictors have a memory of past values?
3. How can this be traded - if the pivot point cannot be determined?
4. Maybe look only for points that can generate income? For example, my target is "the start of drawing of the current segment ZZ will overlap the start of drawing of the next segment ZZ", i.e. the decision to enter the market and classification is made on the next bar, after the change of the vector ZZ, if the segment is long, it usually overlaps the entry point - use a trawl.
5. You need an investor password, from where you get quotes, to get them as well.1) You can choose ZZ parameters yourself, for example by maximal profit. It all concerns the global target, but you can use hundreds of parameters of different ZZ in local targets, it would be of use
2) Predictors are different, if it makes sense to take memory into account, you should take it into account.
3) First: We can make predictors with local targets that refine the entry point (the target is not the direction of the PZ, but a reverse/non-reversal, etc.)
Second: The better we get to the global target, the more accurate the entries will be
I've made a screenshot of ZZ forecast on the chart somewhere, if I find it, I'll paste it here
I found#17408 I think if I increase the quality to 95% it will be great.
But doing it alone is boring, and ideas are running out, so I came up with the idea - a public dataset, but realized that one (.
4) It is possible, but remember you are working with a local attribute, it's just a part of the puzzle which helps to put it all together
5) I have a simple script that constantly unloads quotes from mt4 into tcht at the end of a candle, then I read it from R and do what I want!)
And how do you get the regularities of a series out of here? The wrong patterns are being squeezed. Too small. Also, separated by a dichotomy. That's why back everything is lossless. And without differentiation you get the archive and back to full match? Those are good crutches. We have to figure out the start and end characters of the archive and pull out the squeezable sections. Comparison of the original and unzipped file is not quite correct.
Not a bad article on feature extraction
https://towardsdatascience.com/optimize-data-science-models-with-feature-engineering-cluster-analysis-metrics-development-and-4be15489667a
I do not understand what the point is, I do not know how to speak Bourgeois, explain in working peasant language
Not a bad article on feature extraction
https://towardsdatascience.com/optimize-data-science-models-with-feature-engineering-cluster-analysis-metrics-development-and-4be15489667a
cp, all that's left is to isolate and separate all the features of the price range. Too bad the study isn't in full, there's a quote:
A study that uses baby names as indicators of cultural traits in the United States shows that new names are invented compared to using names from past generations.
As indicators of cultural traits they did interestingly. And how with the outside world they compared. What would prove the relevance of the study.
And so the idea of clustering by the same behavior of traits norms.
How's that?
without the docs on the archiver can not. The point of archiving, present a long known to the archiver pattern in a shorter code, the codes have signs of beginning and end, as in Peter Konov in the recording of medjs in a string, not in a matrix. Archive is a string, there is no other way.
What is the point I do not understand, I do not know how to bourgeois, explain in working peasant
in chrome download the plugin that translates selected text.
cps, now all the features of the price range must be highlighted and separated. Too bad the study is not given in full, there is a quote:
How indicators of cultural traits they did is interesting. And how did they compare with the outside world. To prove the relevance of the study.
And so thoughts of clustering on the same behavior of trait norms.
Yes, I keep thinking in the direction of clustering... but so far I'm too lazy
without the docs on the archiver can not. The point of archiving, present a long known to the archiver pattern in a shorter code, the codes have signs of beginning and end, as in Peter Konov in the recording of medjs in a string, not in a matrix. The archive is a string, there is no other way.
You can take any archiver with open source, presses + - the same. But I do not understand it. Again, the sense of fiddling? With the same distribution of price and random compresses + - the same.
You can take any archiver with open source, compresses + - the same. Only I do not understand it. Again, the sense of fiddling? With the same distribution of price and random compression + - the same.
From the code, too, you can look if something there is equal, then replace it, and see what they replace it with. In any case, to make sense it is necessary to understand the compression algorithm and compression character codes and to analyze the result of compression. So we understand that some regularities the archiver finds and that's all. Send me a link to the open source code of the archiver, I'll take a look.
Yes, I keep thinking in the direction of clustering... but so far I'm too lazy
First of all, I would like to define the attributes, by one increment and time is not very good for me. I have to write my thoughts about problem statement at least)))) so far there are only fragments of thoughts...