Machine learning in trading: theory, models, practice and algo-trading - page 2154
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
I'll say it again, for the dumb ones.
I must be dumb))) or maybe a hangover prevents me ...
But I do not understand what you want to do with this spray, maybe a picture or something, for the complete so to speak)
I'll say it again, for the stupid.
There are points in the feature space. Some are to buy, others are to sell.
Suppose these points can move in such a way that the buy-sell sequence is not observed, i.e. the information about the spread in the dataset is lost.
the spread can be equated to the Euclidean distance between points, or between two classes of points
How to add this information. FNF, acceleration and other stuff you can shove in your s. This is for clarity of perception, so to speak.
Are points in space really stirring the minds of giants of thought?
I must be stupid))) or maybe a hangover prevents me ...
But I do not understand what you want to do with this spread, maybe a picture or something, for complete so to speak )
I already drew a picture and wrote a bunch of text as for complete dumbasses, but it is useless
https://www.mql5.com/ru/forum/86386/page2125#comment_19276126
https://www.mql5.com/ru/forum/86386/page2126#comment_19277425
and there's something written between the two posts too
These morons will shit all over the thread again.
The topic is very important and relevant.
Vladimir, I have an idea to create a rule generator using genetics, but the rules are not primitive like Forest, not limited to a table "X" with examples and n lines, the rules are not limited to anything, it's a full global enumeration of "everything with everything"
How do you see such a fitness function ?
I've already drawn pictures and written a bunch of text as for complete geeks, but it's useless
https://www.mql5.com/ru/forum/86386/page2125#comment_19276126
https://www.mql5.com/ru/forum/86386/page2126#comment_19277425
and there's something written between the two posts too
These assholes are going to shit all over this thread again.
You won't believe it but I read that post and visually remember
And it is not necessary to have only one post of yours or someone else's
That's what articles are written for
;)
I already drew pictures and wrote a bunch of text like for total dowsers, but it's useless
I noticed a long time ago who the texts and posts were for. It's good that I confessed.
For example. There are facial recognition programs. How do they work?
They take certain facial points and combine them into one mathematical model.
And that's what you need to do in the market. You have to build a rigorous mathematical model, not a blurry blur of indicators.
This can only be achieved by working directly with the price.
You haven't answered the question on the merits - fine.
What do you offer me, cooperation, exchange of experience?
I've already drawn pictures and written a bunch of text as for complete geeks, but it's useless
https://www.mql5.com/ru/forum/86386/page2125#comment_19276126
https://www.mql5.com/ru/forum/86386/page2126#comment_19277425
and there's something written between the two posts too
These morons will shit all over the topic again
What the hell is an atr?)) I'm talking about preprocessing that will allow you to give the model even a minute or a day of data and it will always see the same thing ...
I'll draw and show you how to do it, it's useless to explain.
So it would be a very strong leveling, but it may be suitable for the task. However, the development of the event depends on the speed, i.e. what will be the interval ZZ, you can then take it into account separately.
I chose it, there is a 50/50 split, but the higher TF the better it is, I also noticed that my ZZ is somehow glitchy.
The higher the TF, the less observations.
My ZZ is built with Doncian's channel, it can be built with any channel, which eliminates 99% of the glitches.