Discussion of article "Practical application of neural networks in trading" - page 2
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
It is cool, of course, but without the possibility to repeat it, the value of the article is purely theoretical. Like - I did it, and you should try it.
A robot signal based on the article would be a good incentive to try.
And some people will be able to repeat it on their own systems, if they know what you input (specific indicators with specific parameters, returns, etc.) and what you teach (I assume the price, but for how long in advance? For 5 minutes, for an hour, for 1 point or for several points in 5 minutes increments, etc.) What is the trading algorithm, for example, when the predicted price exceeds some value. Or something else?
1. I train the neural network on self-written indicators, which are calculated on two or three timeframes.
2. The parameters of the indicators - by experience.
3. I train the ratio of extreme prices of the daily period to the close. As an option. At the moment there is another vision of what to teach, but we need to check.
4. The trading algorithm is a neural network. And here we have a dilemma - can we help it with our hands or not?
It is cool, of course, but without the possibility to repeat it, the value of the article is purely theoretical. Like - I did it, and you should try it.
A robot signal based on the article would be a good incentive to try.
And some people will be able to repeat it on their own systems, if they know what you input (specific indicators with specific parameters, returns, etc.) and what you teach (I assume the price, but for how long in advance? For 5 minutes, for an hour, for 1 point or for several points in 5 minutes increments, etc.) What is the trading algorithm, for example, when the predicted price exceeds some value. Or something else?
I don't want to contact with signals, but as an option (I wrote earlier) I think to provide trained modules for testing.
And this is where the dilemma arises
the dilemma is described in the message:
Neither to repeat nor to check. And hand-to-hand calculations in Excel are for the 9th grade of high school, but not for a programmer. Strange article.
where is the reproducible MathLab/MQL example? where is the full steit? why is the deposit chosen so impressive? why 53811 test bars and only 402 trades on H1 = average holding time of 133 hours? why is the expectation matrix 80 - in my opinion this is a dubious result?
.....one why, in general, and the discussion has been reduced to trivial guessing at the coffee grounds, imho.
the dilemma is described in the message:
where is the reproducible MathLab/MQL example? where is the full-state? why is the deposit chosen so impressive? why are 53811 test bars and only 402 trades on H1 = average holding time 133 hours? why is the mat.expectation 80 - in my opinion this is a questionable result?
.....one why, in general, and the discussion has been reduced to trivial guessing at the coffee grounds, imho.
The purpose of the article is not to show the profitability of any strategy (the article shows a private variant), but, let's say, to show the prospect of another direction in trading. And frankly speaking, I wonder why we still use third-party software products and programming languages for neural network analysis of currency movements?
The purpose of the article is not to show the profitability of any strategy (the article shows a private variant), but, let's say, to show the prospects of another direction in trading. And frankly speaking, I wonder why we still use third-party software products and programming languages for neural network analysis of currency movements.
The purpose of the article is not to show the profitability of any strategy (the article shows a private variant), but, let's say, to show the prospects of another direction in trading. And frankly speaking, I wonder why we still use third-party software products and programming languages for neural network analysis of currency movements.
I remember that once there was no strategy tester in the terminal. And we had to invent testers on scary hardware ourselves. Maybe the developers of mql5 will do their best????
Of course, not everyone does. Some people just push buttons.
As for neural networks... We don't offend our own personal neural network, which we have in our skulls, just with the multiplication table.
As a minimum, there are two more variants of more meaningful use of indicators.
Similarly for the second question. There is a bearded joke about this in the OPC.
The purpose of the article is not to show the profitability of any strategy (the article shows a private variant), but, let's say, to show the prospects of another direction in trading. And frankly speaking, I wonder why we still use third-party software products and programming languages for neural network analysis of currency movements.
Yes, why do you use third-party software?
Yes, why do you use third party software?
Looking at your rating - of course you can do everything yourself, but most traders can't. You need ready-made neural networks integrated into the terminal, let's say at the level of indicators.
Yes, why do you use third party software?
And as for me personally - that's why I use it, I'm not a programmer, mathematician, etc. And with this to say that "higher matters" are available to many, if only there was a desire))))