Machine learning in trading: theory, models, practice and algo-trading - page 722
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
Do you think there is a prospect for automation:
Sergey, of course!
And then the tester will show the prospects of this indicator.
Freelance will help, but do not forget the source code in the terms of reference
It recognizes it normally, but I cannot choose the right entry point. I want to teach the network to recognize not the appearance of a candle, but the actual moment of entry without the subsidence down. My stops take everything away.
I cannot write such a condition. Maybe someone will tell me?
I can't check it in the tester, because it does not work there due to integration with neuronics. It is written in python and information is exchanged through the file and the tester does not create this file.
There are such models of GARCH. We know from them that the pullback of price increase is more probable than the continuation of price increase. You confirm this truth.
Dr. Trader's advice is not simple.
A fresh book on deep learning is out in Russian:
Goodfellow J., Bengio I., Courville A.Deep Learning is a type of machine learning that empowers computers to learn from experience and understand the world in terms of a hierarchy of concepts. The book contains
the mathematical and conceptual foundations of linear algebra, probability theory and theory
information, numerical computation, and machine learning to the extent necessary
to understand the material. Deep learning techniques used in
practice are described, including direct propagation deep networks, regularization,
optimization algorithms, convolutional networks, sequence modeling, etc. Applications such as natural language processing, speech recognition, computer
vision, online recommendation systems, bioinformatics, and video games are reviewed at
.
The publication is intended for undergraduate and graduate students as well as experienced programmers
who would like to apply deep learning as part of their products or platforms.
UDC 004.85
LIBC 32.971.3
Link from rutracker I can throw in the personal. The book is exceptionally interesting.
Good luck
A fresh book on deep learning is out in Russian:
Goodfellow J., Bengio I., Courville A.Deep learning is a type of machine learning that empowers computers to learn from experience and understand the world in terms of a hierarchy of concepts. The book contains
the mathematical and conceptual foundations of linear algebra, probability theory and theory
information, numerical computation, and machine learning to the extent necessary
to understand the material. Deep learning techniques used in
practice are described, including direct propagation deep networks, regularization,
optimization algorithms, convolutional networks, sequence modeling, etc. Applications such as natural language processing, speech recognition, computer
vision, online recommendation systems, bioinformatics, and video games are reviewed at
.
The publication is intended for undergraduate and graduate students, as well as experienced programmers
who would like to apply deep learning as part of their products or platforms.
UDC 004.85
LIBC 32.971. 3
Link from rutracker I can throw in the personal. The book is exceptionally interesting.
Good luck
There are no non-stationary series generated by indeterminate processes among the list of applications.
Is there any justification of deep networks for financial series?
I found a link to something about that book -http://www.filedropper.com/--2018
(the link and site are not mine)
Among the list of applications there are no non-stationary series generated by uncertain processes.
Is there any justification anywhere for the possibility of applying deep networks to financial series?
Why do you need someone else's justification? You create predictors, build a model, train/test and draw your own conclusions. Whether it is possible/reasonable to apply that model to your predictors.
I only do classification. And in my experience neural networks (not just deep ones) do this very well. Have a look at the last article on ensembles. The results are very good and with significant room for improvement.
Good luck
Among the list of applications there are no non-stationary series generated by uncertain processes.
Is there any justification for the possibility of applying deep networks to financial series?
He is not a trader. It is high time to understand that there is no one to ask :)
He is not a trader. It's high time to understand, there is no one to ask :)
What does it matter if he is a trader or not? He's right on the core of the question.
What does it matter if he is a trader or not? He is right on the essence of the question.
He did not answer the essence of the question, and the question was a cornerstone
The question was a cornerstone one, to say the least - training with a teacher is not suitable for work with non-stationary processes, it's written about it in any book. Hence all this data satanism and the cantankerousness of stationarity, normalization, etc.
It's not that I discourage anyone from doing anything, but sometimes it's useful to say it a few times, so that people get it in their subcortex
He did not answer the essence of the question, and the question was a cornerstone
If not to say more - training with the teacher in principle is not suitable for work with non-stationary processes, it is written about it in any books. Hence all this data satanism and cantankerousness on stationarity, normalization, etc.
Where is it written that teaching with a teacher requires stationarity?
What you call kamlanie, repeatedly proved, mountains of publications, but about training without a teacher for the trade there is nothing at all.