Dear JCL,

thanks for your lovely trading system.
Recently I have read your last article on Deep Learning and tried to experiment some things.
Very intersting article, my compliments.
I have tried to apply this strategy to multiple assets, modifing the code in this way:

Code:
while(asset(loop("EUR/USD","USD/JPY","AUD/USD","EUR/JPY"))) {	   
		if(adviseLong(NEURAL+BALANCED,0,
			change(1),change(2),change(3),change(4),
			range(1),range(2),range(3),range(4)) > 0.5) 
			enterLong();
		if(adviseShort() > 0.5) 
			enterShort();
}



The problem is that if I Train/Test this strategy individually on each pair, I get positive results.
But if put all together in one multiple asset strategy, I do not get the sum of the results I am getting individually and sometime I am getting a completely failing strategy.
So my question is, with the respect to the manual:

[text]
NEURAL_SAVE Data Save all trained models in the file with the name given by the string Data. The function is called at the end of every WFO cycle in [Train] mode.
NEURAL_LOAD Data Load all trained models from the file with the name given by the string Data. The function is called at the begin of every WFO cycle in [Test] mode, and at the begin of a [Trade] session. It is also called every time when the model file is updated by re-training.
[/text]

I have noticed that even with multiple assets, only one file containing the trained model is created.
Could you please tell me:


  • Does this file contain the information for each currency pair?
  • Is there any way to make Zorro writing a different file for eacy currency pair at the end of each WFO cycle?



I hope I have been clear enough. If not, please tell me.
Thanks.
Regards.