Discussion of article "Self-optimization of EA: Evolutionary and genetic algorithms"

New comment
 

New article Self-optimization of EA: Evolutionary and genetic algorithms has been published:

This article covers the main principles set fourth in evolutionary algorithms, their variety and features. We will conduct an experiment with a simple Expert Advisor used as an example to show how our trading system benefits from optimization. We will consider software programs that implement genetic, evolutionary and other types of optimization, and provide examples of application when optimizing a predictor set and parameters of the trading system.

It is important to define the following for solving the optimization task:

  • parameters that will be optimized;

  • optimization criterion — scalar that needs to be maximized/minimized. There can be more than one criterion;

  • target (objective, fitness) function that will calculate the value of optimization criterion.

A fitness function in our case will consistently implement the following:

  • forming the initial data frame;

  • dividing it into train/test;

  • training the model;

  • testing the model;

  • calculating optimization criterion.

Author: Vladimir Perervenko

 
Sincere congratulations!
 
СанСаныч Фоменко:
Sincere congratulations!

Thank you.

Use it.

 
And how to understand what is the total set of predictors for the section"Finding the best combination of predictors" and how they were obtained (it is clear that they are indices, but there is no link to MT or other source of quotes)? There is one mention in the text -"We use the same data and functions as in the previous article" - but there is no link to the article as such.
 
Stanislav Korotky:
And how to understand what is the total set of predictors for the section"Finding the best combination of predictors" and how they were obtained (it is clear that they are indices, but there is no link to MT or other source of quotes)? There is one mention in the text -"We use the same data and functions as in the previous article" - but there is no link to the article as such.

This article is meant.

The source data and functions are also there.

Good luck

 
Are you a programmer, biologist and cyberneticist?
 
By the way, that's why the theory of evolution is called a theory, as it is unproven.
 
Реter Konow:
Are you a programmer, biologist and cyberneticist?
What are you interested in?
 
Реter Konow:
By the way, the theory of evolution is called a theory because it is not proven.
It should be in the annals ))))
 
Комбинатор:
That should go in the annals ))))

Probably, yes.

But: "... search for the optimal value, where the value is a complex function depending on some input parameters...". Already on the second year of Kiev Higher Military Aviation Engineering School I would not be able to pronounce this phrase.... Moreover, at quite civil and general education department of mathematics. The author is not very good at understanding optimisation in general and the target function in particular. Strictly imho.

 
Алексей Тарабанов:

Probably yes.

But: "... search for the optimal value, where the value is a complex function depending on some input parameters...". Already in the second year of the Kiev Higher Military Aviation Engineering School I would not have been able to utter this phrase.... Moreover, at quite civil and general education department of mathematics. The author is not very good at understanding optimisation in general and the target function in particular. Strictly imho.

I don't want to offend anyone. How long have you been wearing a harness?
1234
New comment