Discussion of article "Creating Neural Network EAs Using MQL5 Wizard and Hlaiman EA Generator" - page 10
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
The pictures given by you say just the opposite: it is impossible to use your Expert Advisor under any circumstances, because at the very beginning there is an unexplainable jump in profit, which is then squandered for a long time. And if this jump in profit is removed (who said that real trading will start with such a jump?), then in the first picture we see a fall, and in the second picture - eventually profit with intermediate drawdowns.
My article was published on the site, which shows that the problem is not in the model (neural networks or something more efficient), but in the initial data. The application of Rattle is shown, those who wish can buy a book from me, which is an extended version of the article. So with the help of Rattle you can understand one very simple and extremely important thing: the problem is not in the algorithm, but in the source data, which may or may not generate overtrained models. Here Rattle helps to experiment with input datasets in order to select those that do not lead to overtraining (overfitting).
And the choice of model is a tenth matter.
PS.
According to my research, the use of any kind of MA gives overtrained models, i.e. models that show excellent results on historical data and absolutely unprofitable on real data.
As for your doubts about the results of the EA test and conclusions - considering that the test runs were performed on the H4 timeframe and the test is completely forward - your doubts about its reality are groundless. Firstly, the jumps that frightened you are just large deals on long trends, defined between the intersections of moving averages with the price chart, to understand this, it was enough to enable visualisation in the tester or, if you are a programmer, take a glimpse into the source code of the Expert Advisor, which is included in the MT4 terminal, and secondly, there is no reason to expect that it would not be the same in real trading, as the impact of delays, slippages and spreads of real trading on such large timeframes is practically unaffected.
As for the performance of the idea and the Expert Advisor itself on moving averages - the Expert Advisor given in the example is not for analysing the quality of MetaQuotes software or the efficiency of using MA indicators, since both the first and the second have long been recognised in the industry and IMHO do not require additional evidence.
This EA is a demonstration of a new feature of the Hlaiman EA Generator engine, which consists in the possibility of improving ready-made Expert Advisors by generating an auxiliary neural network filter. Moreover, to train the neural network filter in the tester, the trading chart of this EA and the initial quotes flow are used, i.e. no indicators called by the EA are used for training.
This training mode allows you to filter out not only erroneous signals of any number of indicators, candlestick figures, PA patterns, etc., but also some managemechanagement errors.
As for thearticle and the book you advertise - respect for the useful theoretical material, but let's not refute established concepts on their basis, at least until there is no illustration of the main criteria of truth - your practical results.
Write an interesting article with implementation in the Market - a bonus will be a thread with its discussion, where you won't be banned for this.
Besides Moving Average, can it generate using other indicator?
The improvement of any indicators or EAs can be tried through trained neural networks and in most cases it will succeed.
To do this on your own indicator or EA, you can use the tools in the Hlaiman EA Generator or a separate library.
In this example, the training of the neural network filter executed on the trading results of the original Moving Average for 2014, the latest EA update - March 2015.
In order to test the effectiveness of the filter I ran adviser in the tester for the entire period since the publication, ie from April to August the current date.
The first run made with a disabled filter (corresponding to the original Moving Average), and the second with the enabled filter (see. The marked variable UseNeuro = true), here are the results:
Thus, we can see that training in the past year, the neural network filter, over time, has remained effective and can increase the productivity of trade almost doubled.
This is awesome! do you have hapen to have any recent example? a long term test? I'm interested in purchasing the software, however the site seems abandoned (it even has the default template texts on FAQ).
This is awesome! do you have hapen to have any recent example? a long term test? I'm interested in purchasing the software, however the site seems abandoned (it even has the default template texts on FAQ).
Now with partners, we are completing the development of a new version of the Hlaiman EA Generator with new unique neural network(P-Net) components that are hundreds of times ahead of known analogs.
Recently I posted in the forum one of the example of the automatically generated EA.
https://www.mql5.com/ru/forum/86386/page649#comment_6508250
Yes, you are right, we had some abandonment, as in machine learning(ML) in general, but now everything has changed for the better.
Now with partners, we are completing the development of a new version of the Hlaiman EA Generator with new unique neural network(P-Net) components that are hundreds of times ahead of known analogs.
Recently I posted in the forum one of the example of the automatically generated EA.
https://www.mql5.com/ru/forum/86386/page649#comment_6508250
Very nice, Ill be attentive, do you have a launch date?
Very nice, Ill be attentive, do you have a launch date?
At next week we launch the testing phase.
Testing the artificial neural network P-net, included in the Expert Advisor for the Forex market.
https://www.youtube.com/watch?v=WfH_enerXng
Did you make a Peanut Generator? xD
Yum!