Using neural networks in trading - page 24

 
Actually, I need to try another idea, I won't be able to sleep in peace anyway.
 
TimeMaster:
Or can anyone tell me where else to go with neural networks?
Not much depends on the network itself
 
TheXpert:
There is little to do with the network itself

The net(s) is just a tool, an indicator, with which I try to find the current state of the market at the moment. I think you can compare the current state with the previous one and make a forecast. You can also make a forecast mentally (with your brain). This is what I understand by using neural networks in forecasting.
 
TimeMaster:
The net(s) is just a tool, an indicator, with which I try to find the current state of the market at the moment. I think you can compare the current state with the previous one and make a forecast. You can also make a forecast mentally (with your brain). This is what I understand by using neural networks in forecasting.

Using NS for pattern recognition
 
Debugger:

By the way, data preparation plays no role in this case. I don't have it at all.

The data comes in raw.


It's nothing - you go fishing, and there's a 100-kilo sturgeon in there. And inside he's got five kilos of trout. Wow.
 
Demi:

Using NS for pattern recognition
Interesting topic, I caught a glimpse of it. But I didn't go any further than trying to zoom in on pictures with neural networks.
 
TimeMaster:
It's an interesting topic, I've caught a glimpse of it. But I didn't go further than trying to increase pictures with neural networks.

well, that's what they were designed for....

And it is possible to predict instead of NS by non-linear regression, but you will have to determine the type of regression by yourself, anltchsky.

 
Demi:

well, that's what they were designed for....

And instead of NS, you can also predict with non-linear regression, but you will have to determine the type of regression yourself, anltchically.

In its most generalized form I can say that coefficients of regression are essentially searched with networks, and analytics is done with clustering.

Plus there's all sorts of things like lot size and stop management.

 
TimeMaster:

In its most generalised form, I can say that networks are essentially used to look for regression coefficients, and clustering is used to perform analytics.

Plus there's all sorts of lot size and stop control.

Complication does not lead to anything good.
 
LeoV:
Complicating things doesn't do any good.


I can make an even crazier point.

I don't think you will argue that neural networks are much, much "dumber" than the human brain.

Well, using them in trading just makes the whole picture so much simpler.

IMHO...