All about MQL5 Wizard : create robots without programming. - page 4

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 16): Principal Component Analysis with Eigen Vectors

Principal Component Analysis (PCA) is the focusing on only the ‘principal components’ among the many dimensions of a data set, such that one is reducing the dimensions of that data set by ignoring the ‘non-principal’ parts.

PCA though, with eigen values & vectors, take on a slightly deeper approach. Typically, data sets that are handled under PCA are in a matrix format and the principal components, that are sought from a matrix would be a single vector column (or row) that is most significant among the other matrix vectors and would suffice as a representative of the entire matrix. As alluded in the intro above, this vector alone would hold the main components of the entire matrix, hence the name PCA. Identifying this vector though does not necessarily have to be done by eigen vectors & values, as Singular Value Decomposition (SVD) and the Power Iteration are other alternatives.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 17): Multicurrency Trading

This article continues the series on how the MQL5 wizard is ideal for rapid testing and prototyping ideas for traders. For a lot of people developing expert advisers and trade systems, the need to keep learning and be abreast with trends in not just machine learning but trade & risk management in general is important. We therefore consider within these series how the MQL5 IDE is useful in this regard by not only saving time but also minimizing coding errors.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 18): Neural Architecture Search with Eigen Vectors

We continue the series on MQL5 wizard implementation by looking into Neural Architecture Search while specifically dwelling on the role Eigen Vectors can play in making this process, of expediting network training, more efficient. Neural networks are arguably the fitting of a curve to a set of data in that they help come up with a formulaic expression that, when applied to input data (x), provides a target value (y) just like a quadratic equation does with a curve. The x and y data points though can be, and in fact are often, multidimensional, which is why neural networks have gained a lot of popularity. Nonetheless, the principle of coming up with a formulaic expression does remain, which is why neural networks are simply a means of arriving at this but not the only way of doing so.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 19): Bayesian Inference

We continue our exploit of MQL5 wizard by reviewing Bayesian inference, a method in statistics that processes and updates probabilities with each new information feed. It clearly has a broad spectrum of possible applications, however for our purpose as traders, we zero in on its role in forecasting time series. The time series open to traders for analysis are primarily prices of the traded securities, but as we’ll see in this article, these series could be ‘expanded’ to also consider alternatives like security trade history.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 20): Symbolic Regression

We continue these series where we look at algorithms that can be quickly coded, tested, and perhaps even deployed all thanks to the MQL5 wizard that not only has a library of standard trading functions and classes that accompany a coded Expert Advisor, but also has alternative trade signals and methods which can be used in parallel with any custom class implementation.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 21): Testing with Economic Calendar Data

We continue the series on wizard assembled Expert Advisors by looking at how economic calendar news could be integrated in an Expert Advisor during testing to either confirm an idea or build a more robust trade system, thanks in no small part to this article. That article is part of a series since it is the first, and therefore I encourage readers to read & follow up on it however, our take here is strictly on how wizard assembled Expert Advisors could benefit from these MQL5 IDE tools. For new readers, there are introductory articles here and here on how to develop and assemble Expert Advisors by the MQL5 Wizard.

[Roman Shiredchenko]

Sergey Golubev #:

MQL5 Master Techniques you should know (Part 20): Symbolic Regression

We continue the series of articles in which we consider algorithms that can be quickly coded, tested and possibly even deployed thanks to the MQL5 Wizard, which not only has a library of standard trading functions and classes that accompany the coded Expert Advisor, but also alternative trading signals and methods that can be used in parallel with the implementation of any custom class.

Is it available in Russian?

[Sergey Golubev]

Roman Shiredchenko #:
Is there one in Russian?

This thread (where we are now) is an auto-translated thread from the English forum (this is the English thread).

As for the articles, the early articles have been translated from English into Russian, Japanese, Portuguese, Spanish and German.
Later articles - not yet.

[Roman Shiredchenko]

Sergey Golubev #:

This thread (where we are now) is an auto-translated thread from an English-language forum (this is an English-language thread).

As for the articles, early articles have been translated from English into Russian, Japanese, Portuguese, Spanish and German.
Later articles - not yet.

Opps. Understood.

[Sergey Golubev]

MQL5 Wizard Techniques you should know (Part 22): Conditional GANs

Conditional Generative Adversarial Networks (cGAN) are a type of GAN that allow customization to the type of input data in their generative network. As can be seen from the shared link and in reading up on the subject, GANs are a pair of neural networks; a generator and a discriminator. Both get trained or train off of each other, with the generator improving at generating a target output while the discriminator is trained on identifying data (a.k.a. the fake data) from the generator.

What are the benefits of cGAN to financial time series forecasting? Well the proof is in the pudding as they say which is why we’ll perform some tests towards the end of this article as is the practice, however in image recognition GANs certainly carry some clout even though they do not fare as well as CNNs or ViTs due to their compute expense. They are reportedly better, though, at image synthesis and augmentation.