Machine learning in trading: theory, models, practice and algo-trading - page 2028
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
The basic area for econophysics (potential game theory) does not seem to be reflected there at all.
There collection of articles, the first one does not, the second one Maslov has some and complicated. BUT even Kolmogorov, as well as I could not understand why discrete numbers, which we initially receive and process on the computer we seek to represent a continuous function))))
Bogolubov's principle of an energetically advantageous state is very similar to the aspirations of a market participant).
Yes, my frivolous statement that predictions should be different at different scales depending on the properties of the series is apparently not true).
Max hello, I've glanced through your progress and I want to help you!!!!!
It turns out that there are weekly options, which are responsible for the whole price movement. I do not know about the CME, but in my country for the instrument Si, it is from Thursday to Thursday. That is, the weekly option expires on Thursday. You should use these days for training the models and perhaps the result will be more stable at the end of the week. That is, the option expires on Thursday, so you should take the training period ending on the current Thursday and beginning a week ago, but from Friday. That would take the training period for the full number of weekly options. say I take the last 8 options back. With the close on Thursday. No thanks!!!
Max hello, I've glanced through your progress and I want to help you!!!!!
It turns out that there are weekly options, which are responsible for the whole price movement. I do not know about the CME, but in my country for the instrument Si, it is from Thursday to Thursday. That is, the weekly option expires on Thursday. You should use these days for training the models and perhaps the result will be more stable at the end of the week. That is, the option expires on Thursday, so you should take the training period ending on the current Thursday and beginning a week ago, but from Friday. That would take the training period for the full number of weekly options. say I take the last 8 options back. With the close on Thursday. No thanks!!!
thanks for the useless info.
Thanks for the useless information
Did he mess with the network again?)
Did he mess up the network again? It trades backwards)
I'm sick of it... for some reason sometimes it reverses trades as if
i will look into it again... everything was good, what happened again?
there may be bad series with drawdowns, for example
But I do not like the current series, apparently the error has remained
I'm sick of it... for some reason sometimes it flips deals as if
I will look into it again... everything was good, what happened again?
there may be bad series with drawdowns, for example
but i don't like the current series, i think the error is still there
Take the model and simulate the trading in python, for those two days that the grid is trading...
If it is possible, the grid is already the present one and not the day before yesterday
Take the model and simulate trading in Python, for the two days that the grid has been trading...
If it's possible, the grid is current, not from the day before yesterday.
I checked it, it works better in the tester. I will look into it again )
i just got into recurrence... they learn very well
Z.U. did it right - very sadly learning.
thought love, but no - experience again ))
I've got the dates, now I don't know how to process it, I don't have that much power((((
Right now it's a csv with one column of indexes, weighs a gig. After "decoding" the binary will weigh 17 times more.
Who needs it?
I've got the dates, now I don't know how to process it, I don't have that much power((((
Right now it's a csv with one column of indexes, weighs a gig. After "decoding" the binary will weigh 17 times more.
Who needs it?