Machine learning in trading: theory, models, practice and algo-trading - page 1089
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
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
Educate yourselves while they give it to you :) classics
https://drive.google.com/open?id=1ZzH2TLv13tD0Fjt6htVZiBl5n-Ytt9q-
read thoughtfully and discuss on topic
Brief gist of the method: a priori regularities are not known or their understanding is very limited. Objective: to find a working model among a large number of brute force (bruteforce or genetics) methods
Relevant for virtually the entire range of trading algorithms
If someone has a good understanding of the subject, then we can discuss the realization of the TS, all the tools are available for that, without leaving the mql5 sandbox
kudos to me for my selection of useful literature from the pile of dull G.Such a cool feeling)) When you recommend literature, you get mocked, and then the same person who mocked you recommends the same literature.
I didn't have that )
Max)) And when you've played with functional data and understand that there patterns can not be found, you'll start thinking about levels), and then you may begin to read N. Kamynin.)
What do I know? I'm just a nerd.
Educate yourselves while they give it to you :) classics
https://drive.google.com/open?id=1ZzH2TLv13tD0Fjt6htVZiBl5n-Ytt9q-
read thoughtfully and discuss on topic
Brief gist of the method: a priori regularities are not known or their understanding is very limited. Objective: to find a working model among a large number of brute force (bruteforce or genetics) methods
Relevant for virtually the entire range of trading algorithms
If someone will have a good understanding of the subject, then we can discuss the realization of the TS, all the tools are available for that, without leaving the mql5 sandbox
Give me kudos for my selection of useful literature from the pile of dull G.Like, it is really interesting
We'll discuss it tonight.
Like, really interesting.
let's discuss it tonight
What to discuss? Stationary processes..., standard deviation, MNC...
What is there to discuss? Stationary processes..., standard deviation, MNC...
Yeah, I read it.
I'll pass.
Sanych, you know what's missing in this blind graphanalysis of deviations?
There is no key that turns and moves the kotir along the trend...
Please tell me...
About the key...
Well, of course, also about the nightstand...
About garhi please...
I remember, I promised, but stuck in another place, it's 4 months + some other things, in general I repent, no results yet
gentlemen
I'm a listener and a viewer.
No one has yet convinced me that the topic is profitable.
so...
When are you going to shut up... and stop annoying everyone, free us from your presence, poor in spirit.
Maxim, don't get angry. It is a usual discussion. It's a pity not everyone joined in.
Personally, I do not have a bad polynomial of order 1, i.e. just LR
With increasing order, the signal is already unstable and more errors.
It was said above that there is no trend or flat.
Yes, that's a very good approach. Personally, I have excluded only the flat.
I have obtained a permanent trend that can be processed by a neural network.
Most likely it is better to use an algorithm with feedback.
That is, when an error occurs, the NS is retrained.
all the words in one pile? or are there more?
100000000000000
for I'm starting to write neuronics