Sentiment
I personally feel that in order for us to create a truly robust Trading System we need to think outside the box. I also feel that we need to develop new tools rather than try to optimize old methods.
It is amazing to see everyone here work so hard at building systems and for the benefit of all.
I guess that's why I stopped lurking and would like to contribute.
A few things I have been interested in and have been working on.
Spectral Analysis. I have some software to create digital filters of raw price action.
Neural Networks: cool but still boggles my mind.
Market Sentiment: ideas in PDF's Attached
Is anyone interested in brainstorming?
I think I will start with a lagging digital filter on the 30 minute euro.
Nn
Hi!
Im trying to make some neural network indicators for metatrader4, and would like some sugestions, mostly regarding inputs and outputs of the net, and maybe the structure or type of net that you consider the best for this application.
As far as in know the best outputs for financial series forecasting, are price range forcasting, tops or bottoms forecasting, and that tipe of things. Forecasting directly the price (open, close) doesnt get good results because to numerous reasons, for example a little shift on the time between the open time and the close time could change their values considerately.
If anyone has a sugestion i'll be glad to listen to it and try it.
By the way, im no expert neural network programmer, i just have a good overall idea on the subject =P.
Thanks in advance,
JCCHi,
NN is my thesis couple years ago...but almost forgotten now
This idea can refresh my mind again...I think NN based on pattern recognition using backpropagation is good for forex data mining...
I'm prefer using high low data to feed the NN in order to predict the next daily range data..
==============
Hi prasxz!
Nice to see im not alone here
I also think using high and low is much better than using open or close, to be truth i dont really like the open and close values for intraday analisis, as they seem rather inestable values if you make a displacement on when you place your start point.
Median price also looks good, but i prefer high/low as the information loss in less.
I'll probably use a moving average of the high and one of the low. I've found the JMA to be a really good filter in comparison to regular MAs so i'll do my first tests using a short period JMA without phase changes to avoid distorsion.
So far the inputs im considering for predicting future ranges are:
- JMA of High + JMA of Low.
- JMA of Volume.
- ATR.
- Date (Day of Month, ex. Monday, Thuesday...).
The other idea i have in mind is to use NN to forecast news events direction.
I have a quite big database of forex fundamentals since some years, so i may use those as inputs.
As for what type of neural network to use, im still doing some research, backpropagation NNs are the common standard for NNs, but there are others that seem to have very good results, like the time lagged recurrent networks (but they are hard to train and understand). Other idea i had, was to use a Fukushima NN, those are mainly made for image processing, but with some modifications i think they could be used for pattern recognition on timeseries.
Is anyone here using Neural Networks for pattern recognition with Metatrader, and if so, are there any indicators? I think this woudl be a great tool for providing independant confirmation with our standard indicators and systems.
thanks
Is anyone here using Neural Networks for pattern recognition with Metatrader, and if so, are there any indicators? I think this woudl be a great tool for providing independant confirmation with our standard indicators and systems. thanks
Now that would be usefull, don't think I have ever seen one.
Is anyone here using Neural Networks for pattern recognition with Metatrader, and if so, are there any indicators? I think this woudl be a great tool for providing independant confirmation with our standard indicators and systems. thanks
If you are talking about MetaTrader so I remember some development about 1 year ago on some Russian forum (i remember development but don't remember which forum and where). They were developing some Neural Networks indicators for MT3 and MT4. All the indicators with library files were posted for free on their forum as preliminary versions (for testing).
But they stopped the development or came to commercial development ...
I will try to find some preliminary indicators inside my computer.
If you are talking about MetaTrader so I remember some development about 1 year ago on some Russian forum (i remember development but don't remember which forum and where). They were developing some Neural Networks indicators for MT3 and MT4. All the indicators with library files were posted for free on their forum as preliminary versions (for testing).
But they stopped the development or came to commercial development ...
I will try to find some preliminary indicators inside my computer.great
I found it on the other forum here http://forexsystems.ru/phpBB/viewtopic.php?t=47
It is the thread where people are developing Neural Networks indicator for MT4. In Russian language, sorry.
- they started with some e-books and articles;
- then some library files for Delphi 4 (NeuralBase, Neural Network Wizard, GeneBase, SOMBase, WavUtils);
- then they coded many versions of indicator NeuroProba.mql4 (author is Rosh);
- then they tested it and found many bugs and mistakes in calculation.
This thread is not closed yet and seems they are continuing to development (it is necessary to register on their forum to see the attachments).
Besides I found this link about Neural Networks (in English).
I found it on the other forum here http://forexsystems.ru/phpBB/viewtopic.php?t=47
It is the thread where people are developing Neural Networks indicator for MT4. In Russian language, sorry.
- they started with some e-books and articles;
- then some library files for Delphi 4 (NeuralBase, Neural Network Wizard, GeneBase, SOMBase, WavUtils);
- then they coded many versions of indicator NeuroProba.mql4 (author is Rosh);
- then they tested it and found many bugs and mistakes in calculation.
This thread is not closed yet and seems they are continuing to development (it is necessary to register on their forum to see the attachments).
Besides I found this link about Neural Networks (in English).Awsome New Digital! Ill look at the material in a few minutes...gotta break out the russian..which isnt so great, but I think that coupled with AltaVista ill be able to make a decent attempt. Im currently coding in CORTEX on other Neural Networks (NN from now on) and im planning to convert into MQ4...I think we should DEFINATLY keep this thread going because (and this is an opinion) NN are THE future of tecnical anaylsis. NN's, for those who arent geek enough to know..are basically algorythms that mimic the brain (not nessisarily the human brain..cuz that would be Mind bustingly complicated) in that it learns as it goes. Im writing the EAs to give advice on whether or not to take a particular signal based on small patterns that have come before when a similer signal was given. Thats what most NN's do, they search data for small patterns that would be meaningless to us, or even other algorthms and see what those patterns do over time. The first EA will feature Brain Trend. I ask that everyone be patient though, CORTEX coding takes time...rather, it takes time to train the NNs and perfect them. If anyone here is familier with CORTEX or Code conversion, any help would be appreciated. I understand why russian forum would go commercial...NNs are the current style with big money traders. So...what do you guys say?
![MQL5 - Language of trade strategies built-in the MetaTrader 5 client terminal](https://c.mql5.com/i/registerlandings/logo-2.png)
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
You agree to website policy and terms of use
I tried to move some posts and threads to this one concerning the subject about Neural Networks. Just to spen some development up and keep everything in one place.
---------------------
GMDH is known also as Polynomial Neural Networks, Abductive and Statistical Learning Networks.