MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal

Automated Trading and Strategy Testing Forum

Hundreds of Forex Robots from MetaTrader Market at Your Service
To add comments, please log in or register
Do you have a trading signal? Publish it in your blog as well!
MetaQuotes Software Corp.
139477
MetaQuotes 2010.10.27 10:17

New article Growing Neural Gas: Implementation in MQL5 is published:

The article shows an example of how to develop an MQL5-program implementing the adaptive algorithm of clustering called Growing neural gas (GNG). The article is intended for the users who have studied the language documentation and have certain programming skills and basic knowledge in the area of neuroinformatics.


Author: Алексей

Evaluation of Trade Systems - the Effectiveness of Entering, Exiting and Trades in General
There are a lot of measures that allow determining the effectiveness and profitability of a trade system. However, traders are always ready to put any system to a new crash test. The article tells how the statistics based on measures of effectiveness can be used for the MetaTrader 5 platform. It includes the class for transformation of the interpretation of statistics by deals to the one that doesn't contradict the description given in the "Statistika dlya traderov" ("Statistics for Traders") book by S.V. Bulashev. It also includes an example of custom function for optimization.
FXWinner
8
FXWinner 2010.12.15 20:35

Hi Alex,

Thanks for clear explanation on the subject.

Would it be possible to share some practical code for Reconstruction future price, for instance from optimal signals.

The idea is:

1. Input (Source): multiple currencies (18)

2. Destination: Optimal signal of the currency we would like to predict (pic: 2. Optimal_Signals)

3. Find a neuro-connections between Source and Destination and explode it in trading.


2. Optimal_Singnals


Another question about NN reconstruction: 

Is it possible instead of Random Samples use our samples instead , like on pic 2:

Our brain can reconstruct the picture in less then a second, let's see how much time it takes for NN do the same, just a joke, it is not challenge.

NN_Man


Random generated Samples are not very interesting to see as there is no meaning behind or use, however if we can draw dots ourselves with some meaning behind it , it would be much better fun. :-0)

GNG-1


supercoder2006
21
supercoder2006 2012.07.26 19:48

Hi,

Thank you for the great job, this is very exciting.

Can you download the Expert Advisor for this acticle? Can this be tested using Strategy Tester?

 

 

Taggert
6
Taggert 2013.06.21 15:55

Very Interesting,

I am looking forward to implement it and use it instead of a fixed neuronal network.   

Jamel
6
Jamel 2013.11.10 00:11

Hello

i ask if anyone of the community success to develop EA using GNG?

i ask if the result is good ?

thanks

Алексей Субботин
983
alsu 2014.04.09 21:16
Jamel:

Hello

i ask if anyone of the community success to develop EA using GNG?

i ask if the result is good ?

thanks

Well.. after what? five months o_O no one is willing, so maybe I can comment on that myself.

In the implementation you've seen in this article the NN is a self-adapting variant of a so called radial-based functions net. If you compare an EA based upon GNG algorithm to the same type of EA based on a non-adaptive type of clusterization neural network you most probably are going to obtain better results with GNG rather than without it. So, to answer your latter question, yes, the result is good in the sense I just explained.

Turning to the former one, I myself have developed EAs with a GNG inside, and it worked moderately well, yay. However, for everyday use I prefer other algorithms which as a rule are non-neural. I can back it up by reminding that ANN always presents a "black box" meaning that you do not really understand what is going on in there when it processes input data. That implies that ANN would be an algorithm of choice only in a situation when you'd have a completely unstructured set of data with absolutely unknown intrinsic dependencies which you would like for the ANN to somehow extract. Note: without any promise for an accurate result. In any other case, i.e. when you have some ideas about how the dependencies in your dataset may be organized, you'd wanna first try other, more deterministic "white box" ways of structuring it. Thousands of them.

/
To add comments, please log in or register