Self-trained MA cross! - page 8

 
 

Forum on trading, automated trading systems and testing trading strategies

...

Sergey Golubev, 2009.10.09 08:43

Neural Network

Neural Network: discussion/development threads

  1. Better NN EA development thread with indicators, pdf files and so on.
  2. Better NN EA final thread 
  3. taking NEURAL NETWORKS to the NEXT LEVEL - very interesting thread
  4. Neural Networks thread (good public discussion)
  5. How to build a NN-EA in MT4: usefull thread for developers.
  6. Radial Basis Network (RBN) - As Fit Filter For Price: the thread 

Neural Network: Indicators and systems development

  1. Self-trained MA cross!: development thread for new generation of the indicators
  2. Levenberg-Marquardt algorithm: development thread

Neural Network: EAs

  1. CyberiaTrader EA: discussion thread and EAs' thread.
  2. Self learning expert thread with EAs' files here.
  3. Artificial Intelligence EAs threads: How to "teach" and to use the AI ("neuron") EA thread and Artificial Intelligence  thread
  4. Forex_NN_Expert EA and indicator thread.
  5. SpiNNaker - A Neural Network EA thread

Neural Network: The Books

  1. What to read and where to learn about Machine Learning (10 free books) - the post.

The article

CodeBase


 

This is very interestin, I would like to contribute but I don't see where we are now. Do you get some results?

if you want a self learning EA we need neural networks or similar approach, a synthetic way to achieve smthg is post-maintein the EA and optimize it with a rolling fashion.

Regards

 

Forum on trading, automated trading systems and testing trading strategies

How to start with MetaTrader and forex, the beginning

Sergey Golubev, 2021.02.08 16:30

Developing a self-adapting algorithm (Part I): Finding a basic pattern

Developing a self-adapting algorithm (Part I): Finding a basic pattern


Any trading algorithm is generally a tool which may bring profit to an experienced trader or instantly destroy a deposit of an inexperienced one. The issue of creating a profitable and reliable algorithm is that we cannot understand what needs to be done in order to earn money and what methods are used by "successful traders". While HFT, arbitrage, option strategies and calendar spread-based systems boast a solid theoretical basis clearly stating what needs to be done to make profit, the algorithms based on price analysis and fundamental data are much more ambiguous. This area has no full-fledged theoretical basis that would describe pricing making it extremely difficult to create a stable trading algorithm. Trading turns into art here, while science helps systematizing everything.

But is it possible to create a fully automated trading algorithm based only on the analysis of price changes working on any trading instrument without optimization and with no need to manually adjust parameters for each trading instrument separately? Is there an algorithm you can simply apply to a necessary trading instrument chart so that it immediately defines profitable parameters for it? 



 

Forum on trading, automated trading systems and testing trading strategies

How to start with MetaTrader and forex, the beginning

Sergey Golubev, 2021.02.19 18:08

Developing a self-adapting algorithm (Part II): Improving efficiency 

Developing a self-adapting algorithm (Part II): Improving efficiency

Before reading this article, I recommend that you study the first article "Developing a self-adapting algorithm (Part I): Finding a basic pattern". This is not necessary, since the main point will still be clear, but reading will be more interesting.

In the previous article, I detected a simple pattern and developed a very simple algorithm that exploits it. But the algorithm has no flexible structure, and it makes no sense to expect any outstanding results from it.

We need to greatly improve it so that it becomes more flexible and adjusts its operation parameters depending on the market situation so that it is possible to achieve better results and stability.


 
Ahmed Soliman:

Do you think it's achievable idea? let's set on the rounded table!

You would have to find a way to define if you are in a Trend or not and how it is supposed to react to a flat or not, how it calculates StopLoss and TakeProfit based on Market conditions like Trend Volume or Volatility
 
Ahmed Soliman:

Do you think it's achievable idea? let's set on the rounded table!

You need to set the algorithm to acknowledge if there is a trend or not, how it calculates SL and TP based on market parameters like Volumes or Volatility and even imply statistic aspects to tell if a pattern was working and if not how it should alternate. Ideas are not the problem here,  programming is.
 

Forum on trading, automated trading systems and testing trading strategies

How to start with MetaTrader and forex, the beginning

Sergey Golubev, 2021.03.12 09:56

Self-adapting algorithm (Part III): Abandoning optimization

Self-adapting algorithm (Part III): Abandoning optimization

Before reading this article, I recommend that you study the second article in the series "Developing a self-adapting algorithm (Part II): Improving efficiency". The methodology applied in the current article differs significantly from everything discussed earlier, but it will be useful to read the previous articles to understand the topic.


 

This strategy, if it would work, would be the same than artificial intelligence.

   Here it is : "non standart automated trading"


It work with accelerator or awesome indicator, instead of an MA, but the principle is the same.

Do a backtest using different data for accelerator (or ma), and then use the best data for forward trading.

The only difference is : instead of being a "self adaptative expert", one's has to make backtest every week (days) to verify that he still has the best value for his EA.
Non-standard Automated Trading
Non-standard Automated Trading
  • www.mql5.com
Successful and comfortable trading using MT4 platform without detailed market analysis - is it possible? Can such trading be implemented in practice? I suppose, yes. Especially in terms of the automated trading!
 
ffoorr:

This strategy, if it would work, would be the same than artificial intelligence.

   Here it is : "non standart automated trading"


It work with accelerator or awesome indicator, instead of an MA, but the principle is the same.

Do a backtest using different data for accelerator (or ma), and then use the best data for forward trading.

The only difference is : instead of being a "self adaptative expert", one's has to make backtest every week (days) to verify that he still has the best value for his EA.

Interesting.