Taking Neural Networks to the next level - page 31

Jean Francois Le Bas
1246
Jean Francois Le Bas  
Jefferson Metha:

in lower time frames the fractals of higher TF are actually the peaks and troughs

yes they are but you don't trade them as reversals in the Chaos Trading System

https://www.youtube.com/watch?v=bNxt298VVOw
The Practical Fractal: The Holy Grail to Trading by Bill Williams PhD of Profitunity Trading Group
The Practical Fractal: The Holy Grail to Trading by Bill Williams PhD of Profitunity Trading Group
  • www.youtube.com
The Practical Fractal: The Holy Grail to Trading by Bill Williams PhD of Profitunity Trading Group is a 20 year old video from a talk Bill gave after writing...
Pedro Severin
1284
Pedro Severin  

I have a question on this subject. I hope to write as clearly as possible.

I have been trading with neural networks (LSTM, to be precise) and when I trained them, the data was normalized.

But if the data is normalized, should I normalize it every time I perform live operations? I currently do it, but now I have my doubts about whether it is a good idea or not.

I mean ... if the data is normalized every time a new candle is formed, every time the values would be different because I am adding a new candle, and if it is normalized, then the candle that had a value of 1 (for example )  could not have it anymore. Isn't there an inconsistency?

Sergey Golubev
Moderator
120301
Sergey Golubev  

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

Young Ho Seo
80199
Young Ho Seo  
Jean Francois Le Bas:
fractals are not about finding peaks and troughs, you got the "Chaos Theory" trading system wrong my friend


We are not talking about Fractal Indicator by Bill Williams.

We are talking about the Fractal geometry researched by Benoit Mandelbrot, the father of Fractal Research in the world.

https://en.wikipedia.org/wiki/Benoit_Mandelbrot

Fractal indicator by Bill Williams are just one of many technical indicator freely available nowdays.

It is based on reapting pattern but not based on Fratal Wave itself.

Peak Trough Analysis (or Peak Trought Transformation) is the Fractal transformtion that turns entire price series into Fractal pattern helping us to make advanced prediction on financial market. 

Never confuse Fractal Indicator by Bill Williams with Fractal geometry research done by Benoit Mandelbrot.

If you want to go for more advanced market prediction, I will recommend to study Peak Trough Analysis that brings most of mathematical algorithm opened by Benoit Mandelbrot including Fractal Dimension described here.

https://en.wikipedia.org/wiki/Fractal_dimension


Since it is easier to use Fractal Indicator, you might study this first. Then study Fibonacci Retracement and Expansion. Then use Peak Trough Analysis finanally. Then it would open up new trading strategies using price action and patterns.

Never stay in th fractal indicator forever if you want to become more serious trader.

Must move on to more advanced Peak Trough Analysis soon or later.

Mandelbrot set - Wikipedia
Mandelbrot set - Wikipedia
  • en.wikipedia.org
The Mandelbrot set is the set of complex numbers for which the function does not diverge when iterated from , i.e., for which the sequence , , etc., remains bounded in absolute value. Mandelbrot set images may be created by sampling the complex numbers and testing, for each sample point , whether the sequence f c ( 0 ) , f c ( f c...
cemal
1232
cemal  
What does  fibonacci numbers    got to do  with   taking neural networks to the next level?Why  not  open  a  seperate   topic  ?
cemal
1232
cemal  
Pedro Severin:

I have a question on this subject. I hope to write as clearly as possible.

I have been trading with neural networks (LSTM, to be precise) and when I trained them, the data was normalized.

But if the data is normalized, should I normalize it every time I perform live operations? I currently do it, but now I have my doubts about whether it is a good idea or not.

I mean ... if the data is normalized every time a new candle is formed, every time the values would be different because I am adding a new candle, and if it is normalized, then the candle that had a value of 1 (for example )  could not have it anymore. Isn't there an inconsistency?

I  am not an expert on the subject.But as  far  as  I  know    you should normalize your  data(z score,mini max etc..)  and  neural  network   should  predict the percentage change of the price series.    .    

Sergey Golubev
Moderator
120301
Sergey Golubev  

Forum on trading, automated trading systems and testing trading strategies

How to Start with Metatrader 5

Sergey Golubev, 2020.03.12 06:42

Neural Networks Made Easy - MT5 

Neural Networks Made Easy - MT5 article

Table of Contents The Artificial Intelligence is increasingly covering various aspects of our life. A lot of new publications appear, stating that "the neural network was trained to..." However, artificial intelligence is still associated with something fantastic. The idea seems to be very complicated, supernatural and inexplicable. Therefore, such a state-of-the art miracle can only be created by a group of scientists. It seems that a similar program cannot be developed using our home PC. But believe me, it's not that difficult. Let us try to understand what the neural networks are and how they can be applied in trading.

LUIS ALBERTO BIANUCCI
420
LUIS ALBERTO BIANUCCI  
The Mt5 seems more evolved than the MT4, now, can you make money with it?
What is the best 2-year backtestig tick-to-tick profit factor?
[Deleted]  

If you have medical database or sales database or whatever with seasonality and trends you can use all the ML you want.


Markets have not even 1 chance to be tamed and 'learned' by AI, simply because THERE ARE NO PATTERS.

[Deleted]  
Hi,
Thank you so much for your answer. Its really very helpful for me.
Yes, neural network are really flexible, but not all time. 

Thank you..