Machine learning in trading: theory, models, practice and algo-trading - page 668

New comment
 
Aleksey Terentev:
IMHO:

My question was NOT what to write, but HOW often to run your code.

 
Aleksey Terentev:
IMHO:

Yes, I understand, but it does not solve all exchange issues. But semaphores solve everything and uniformly.

 
SanSanych Fomenko:

My question was NOT what to write, but HOW often to run your code.

I have a data exchange every tick.

By the way, did you see my answer to your question about synchronization of exchanges7 About semaphores.

 
Aleksey Terentev:
May I ask, every tick for machine learning model?

Yes, for MO. The NS response is 0.005 s.

 
Aleksey Terentev:

Would you take a moment?

I understand that you are scalping. What is the reason for your choice? Why do you use scalping and neural networks?

Not really scalping. More like scalping with an intrade.

Why is that? I just don't believe in prediction and consider the market random to the observer. Hence, every trade starts with scalping, and then depending on how the process develops.

I.e., if the deal does not go through - scalping will go through.

 
Vizard_:

What do you associate this thing with?

it's a dead Pikachu :)

 
Aleksey Terentev:

You know, if you follow the ideas of philosophy and quantum physics, the observer himself and determines the state of the system. =) But, this is offtop)

And we know these observers.)

 
Aleksey Terentev:

You know, if you follow the ideas of philosophy and quantum physics, the observer himself and determines the state of the system. =) But, this is offtop)

So this is not philosophy, but ordinary physics :) there is nothing surprising there, the fact of observation affects a particle, because to observe it it is necessary to release electrons or photons, which will change its trajectory :) it has nothing to do with the market

 
Maxim Dmitrievsky:

This is not philosophy, it is ordinary physics :) there is nothing surprising there, the fact of observation affects a particle, because to observe it it is necessary to release electrons or photons, which will change its trajectory :) it has nothing to do with the market

It may not have anything to do with the Forex market but it is necessary to do it where there are paid quotes for observation:)

 
I am finally convinced that trying to predict specific events with the help of the NS. That is, learning with a teacher does not lead to anything. I think to look in the direction of learning without a teacher. Self-organizing maps come to mind. They are able to break down the data into classes without assigning output classes. Once you get the classes, you can look at the stories to see what you can get out of them. Generally, this is a new area for me. In general, I have come to a trivial conclusion. TC construction begins with searching for patterns. The method I have suggested is one approach. You can simply study the history visually. This is how it has been done for a long time. That's why the heads and shoulders and so on appeared. But I'm still a programmer, and I want to find algorithms to find patterns. That is, to reduce everything to their software search. Attempts to find materials on this subject have yielded no results. It does not matter if it is neural networks or not. The essence of trading is profit and what methods are used for its obtaining is not important. But again, everything starts with the search for patterns.
1...661662663664665666667668669670671672673674675...3516
New comment
Reason: