Sign Up

Have an account? Sign In Now

Sign In

Forgot Password?

Don't have account, Sign Up Here

Forgot Password

Lost your password? Please enter your email address. You will receive a link and will create a new password via email.

Have an account? Sign In Now

You must login to ask question.

Forgot Password?

Need An Account, Sign Up Here
Sign InSign Up

First independent community of traders

First independent community of traders Logo First independent community of traders Logo

First independent community of traders Navigation

  • Home
  • About Us
  • Blog
  • Contact Us
Search
Ask A Question

Mobile menu

Close
Ask a Question
  • Home
  • Add group
  • Groups page
  • Communities
  • Questions
    • New Questions
    • Trending Questions
    • Must read Questions
    • Hot Questions
  • Polls
  • Tags
  • Badges
  • Users
  • Help
  • Buy Theme
  • Home
  • About Us
  • Blog
  • Contact Us
Home/ Questions/Q 4295
Next
In Process
pvitaly
pvitaly

pvitaly

  • 1 Question
  • 3 Answers
  • 0 Best Answers
  • 20 Points
View Profile
  • 0
pvitaly
Asked: December 27, 20202020-12-27T05:06:52+00:00 2020-12-27T05:06:52+00:00In: Forex Expert Advisors

Robot on neural networks

  • 0

Interested in the experience of developing robots on neural networks. What data do you transmit to the network, on what history and timeframe do you conduct training ?

At the moment, I implemented it in a simple way: we take n-the number of bars and pass it to the grid at the output we get prediction coefficients from 0 to 1 for buying and also for selling

The training was conducted from 2012-2018 on different timeframes risk per trade 2% stop 25/4. 

here’s what happened:

  • 9 9 Answers
  • 0 Followers
  • 0
Answer
Share
  • Facebook

    9 Answers

    • Voted
    • Oldest
    • Recent
    1. greshnik1

      greshnik1

      • 1 Question
      • 8 Answers
      • 0 Best Answers
      • 36 Points
      View Profile
      greshnik1
      2020-12-27T05:08:02+00:00Added an answer on December 27, 2020 at 5:08 am

      Vitaly Palkin:

      Do you suggest manually searching for patterns ? So after training, she just found them. Maybe in history she just remembered when to enter)? 

      Are you sure these are patterns)? Yes, I remember.Of course, it is better to automate the search.Look to the sideVolking – forward optimization. It relies on the fact that patterns must be constant over time. Or, at least, having a small linear “movement” in the space of neural network parameters(in your situation). I hope that I wrote it clearly.

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    2. tormovies

      tormovies

      • 0 Questions
      • 1 Answer
      • 0 Best Answers
      • 22 Points
      View Profile
      tormovies
      2020-12-27T05:07:57+00:00Added an answer on December 27, 2020 at 5:07 am

      Yes, I would like some minimal testing outside the training period 

      because if you test on the learned period will be just a super fit, and so would have taught the network for the entire period minus 6 months and then separately launched for 6 months, at least some would be an approximate result and then such a fit I also did but there was no sense 

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    3. ara66676

      ara66676

      • 0 Questions
      • 4 Answers
      • 0 Best Answers
      • 28 Points
      View Profile
      ara66676
      2020-12-27T05:07:46+00:00Added an answer on December 27, 2020 at 5:07 am

      Vitaly Palkin:

      Do you suggest manually searching for patterns ? So after training, she just found them. Maybe in history she just remembered when to enter)? 

      The fact that a properly assembled NS will find and remember patterns that a person does not see is a fact. The fact that patterns are worked out like all noticeable 50/50 is also a fact. All you did was just find more signals to trade. If you really want to continue, then you need to look a little in a different direction… is input to the neural network such as dates of birth of artists and find a pattern in the development of pricing pair month. That’s when your grid will be worth something. There was a post about decision trees, so this algorithm just makes everything much faster and with much more data. That is, on the trees you collect even more patterns for yourself, but no one guarantees you to work out.

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    4. pvitaly

      pvitaly

      • 1 Question
      • 3 Answers
      • 0 Best Answers
      • 20 Points
      View Profile
      pvitaly
      2020-12-27T05:07:42+00:00Added an answer on December 27, 2020 at 5:07 am

      Aliaksandr Hryshyn:

      This kind of method is not working. There is a lot of “noise”, the network with this approach will not be able to distinguish stable patterns from it.

      Do you suggest manually searching for patterns ? So after training, she just found them. Maybe in history she just remembered when to enter)? 

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    5. greshnik1

      greshnik1

      • 1 Question
      • 8 Answers
      • 0 Best Answers
      • 36 Points
      View Profile
      greshnik1
      2020-12-27T05:07:37+00:00Added an answer on December 27, 2020 at 5:07 am

      Vitaly Palkin:

      Interested in the experience of developing robots on neural networks. What data do you transmit to the network, on what history and timeframe do you conduct training ?

      At the moment, I implemented it in a simple way: we take n-the number of bars and pass it to the grid at the output we get prediction coefficients from 0 to 1 for buying and also for selling

      The training was conducted from 2012-2018 on different timeframes risk per trade 2% stop 25/4. 

      here’s what happened:

      This kind of method is not working. There is a lot of “noise”, the network with this approach will not be able to distinguish stable patterns from it.

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    6. igoreremenko

      igoreremenko

      • 0 Questions
      • 19 Answers
      • 0 Best Answers
      • 58 Points
      View Profile
      igoreremenko
      2020-12-27T05:07:31+00:00Added an answer on December 27, 2020 at 5:07 am

      Vitaly Palkin:

      Interested in the experience of developing robots on neural networks. What data do you transmit to the network, on what history and timeframe do you conduct training ?

      At the moment, I implemented it in a simple way: we take n-the number of bars and pass it to the grid at the output we get prediction coefficients from 0 to 1 for buying and also for selling

      The training was conducted from 2012-2018 on different timeframes risk per trade 2% stop 25/4. 

      here’s what happened:

      you can become a virtual millionaire in the tester without neural networks, in MT4 you can become a billionaire in General)

      this topic is raised on this forum constantly, the last 10 years, something amazing (according to the results) so far no one has shown publicly, maybe you will succeed…

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    7. pvitaly

      pvitaly

      • 1 Question
      • 3 Answers
      • 0 Best Answers
      • 20 Points
      View Profile
      pvitaly
      2020-12-27T05:07:15+00:00Added an answer on December 27, 2020 at 5:07 am

      Petros Shatakhtsyan:

      And you try to run it on MT5, and it is in the mode of Real ticks and you will see that the chart is completely on the turn.

      And you don’t have to wait so long in real life to make sure of this.

      The EA is built on the opening of the 30m bar. ticks are not taken into account   

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    8. pvitaly

      pvitaly

      • 1 Question
      • 3 Answers
      • 0 Best Answers
      • 20 Points
      View Profile
      pvitaly
      2020-12-27T05:07:00+00:00Added an answer on December 27, 2020 at 5:07 am

      And the meaning is that training only on bars worked with a Bang)

      On a real account, the robot is already running, you are interested in who uses what parameters and what training methods are used for neural networks?

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    9. -aleks-

      -aleks-

      • 2 Questions
      • 35 Answers
      • 0 Best Answers
      • 72 Points
      View Profile
      -aleks-
      2020-12-27T05:06:55+00:00Added an answer on December 27, 2020 at 5:06 am

      Vitaly Palkin:

      Interested in the experience of developing robots on neural networks. What data do you transmit to the network, on what history and timeframe do you conduct training ?

      At the moment, I implemented it in a simple way: we take n-the number of bars and pass it to the grid at the output we get prediction coefficients from 0 to 1 for buying and also for selling

      The training was conducted from 2012-2018 on different timeframes risk per trade 2% stop 25/4. 

      here’s what happened:

      So what’s the point of showing results on training data? Show what went beyond training.

      • 0
      • Reply
      • Share
        Share
        • Share on Facebook
        • Share on Twitter
        • Share on LinkedIn
        • Share on WhatsApp
    Leave an answer

    Leave an answer
    Cancel reply

    Browse

    Sidebar

    Ask A Question

    Stats

    • Questions 503
    • Answers 2k
    • Posts 5
    • Comments 0
    • Best Answers 0
    • Users 672
    • Popular
    • Comments
    • Tags
    • forexcommunity

      Highlighting what’s important about questions & Answers on Discy Community!

      • 0 Comments
    • forexcommunity

      Introducing Keyboard Shortcuts, our first Labs feature

      • 0 Comments
    • forexcommunity

      Defining quality on Discy Engine — what a helpful answer ...

      • 0 Comments
    • forexcommunity

      Organizational and company accounts on Discy Engine the next step

      • 0 Comments
    • forexcommunity

      Hello world!

      • 0 Comments

    Related Questions

    • pinupcasinoo

      Pin Up Casino

      • 0 Answers
    • c00l777

      During optimization, indicators that are not present in the robot ...

      • 2 Answers
    • c00l777

      During optimization, indicators that are not present in the robot ...

      • 0 Answers
    • c00l777

      Optimization results differ on different accounts

      • 3 Answers
    • fresto

      Invalid price error occurs

      • 2 Answers

    Users

    pinupcasinoo

    pinupcasinoo

    • 1 Question
    • 0 Answers
    JamesSwics

    JamesSwics

    • 0 Questions
    • 0 Answers
    Charlesnam

    Charlesnam

    • 0 Questions
    • 0 Answers

    Footer

    First independent community of traders

    About

    An independent community of forex traders. This is where traders communicate. You can ask your questions and you will receive an answer to your question.
    • Terms of Use
    • Privacy Policy
    • Cookie Policy
    • Knowledge Base
    • Support

    © 2021 Forexcommunity.net. All Rights Reserved