Discussion of article "Brute force approach to pattern search"

[MetaQuotes]

New article Brute force approach to pattern search has been published:

In this article, we will search for market patterns, create Expert Advisors based on the identified patterns, and check how long these patterns remain valid, if they ever retain their validity.

A neural network is essentially also a kind of brute force. But its algorithms are very different from simple brute force algorithms. I will not provide the details of specific neural network architectures and their elements, but will try to provide a general description. I think, if we stick to a certain architecture, we limit the capabilities of our algorithm in advance. A fixed architecture is an irreparable limitation. A neural network is a kind of architecture of a possible strategy in our case. As a result, the configuration of a neural network always corresponds to a certain file with a network map. This always points to a collection of certain units. It is like with a 3D printer: Set item parameters and the printer will produce it. Thus, a neural network is a general code that does not make sense without a map. This is like taking any advanced programming language and simply creating an empty project without utilizing all its capabilities. As a result, the empty template does nothing. The same is with the neural network. Unlike brute force, a neural network can provide almost unlimited variability in strategies, any number of criteria and higher efficiency. The only disadvantage of this approach is that the efficiency greatly depends on the code quality. An increasing system complexity may lead to increased resource intensiveness of the program. As a result, our strategy is converted into a network map, which is its equivalent. The same is done in the brute force approach, but here we work with a simple sequence of some numbers. This sequence is much simpler than a network map, it is easier to compute, but it also has a limit in terms of efficiency. The below scheme displays the above explanation.

Author: Evgeniy Ilin

[Allan Ferreira]

I just need to reply this article. Patterns are just a small piece of the overall picture.

If higher timeframe shows uptrend, smaller timeframe shows downtrend, a reversal pattern in smaller timeframe means a buy with small SL. 

The most important question: how to make the machine understands what is a trend? 

[cemal]

We need to make the machine  learning to understand the  profitability and the pattern relationship.And this is well explained  in the article.We dont' need it to understand  what the trend is.

My experience is neural networks dont' work in strong trends ,you can check it with bitcoin,crypto currency data series.

[Evgeniy Ilin]

Allan Ferreira:
I just need to reply this article. Patterns are just a small piece of the overall picture.

If higher timeframe shows uptrend, smaller timeframe shows downtrend, a reversal pattern in smaller timeframe means a buy with small SL. 

The most important question: how to make the machine understands what is a trend? 

understand that trend and flat are just substances invented by our brain to simplify understanding of the market. In reality, market situations are endless, and it is impossible to describe all of them in such a limited framework. The task of the machine is to determine which situations are most represented on the market and highlight those that are truly global. This is the task of the machine. The human brain is not designed to analyze large amounts of data, but the machine happily does it. The point of this method is that you don't need to know what the machine has found, you just need to know that it works.

[Al Bundy]

Hi, your work and especially your thoughts are very interesting. You wrote, that both versions mt4 and mt5 are attached. I can't find a mt5 version! ?

Please add if possible.

Many thanks