Machine learning in trading: theory, models, practice and algo-trading - page 2096
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
I'm at a roll-up conference, I'll write later.
at the roll-up conference? )))) okay))
I'll go to the weekly gathering of experts on light tasting, and we'll also discuss the problem of global warming on the planet earth.
I'm going to the weekly gathering of lager tasting experts, and we're going to talk about global warming on Earth.
Will you be watching soccer with your beer?
at the roll-up conference? )))) okay))
I'm going to the weekly gathering of lager tasting experts, and we're going to talk about global warming on planet earth.
that's it.)
I've done some tools, it won't do you any good. If you can't cook the data, it won't do you any good.
It's a good thing, use it.
If the data is not too big, it is more convenient to use it on a local PC. In google colab the kernels are deactivated at idle, you have to re-install all the packages and download the data. The processor there is only 4 cores and tesla is not the most powerful
+ Yes, I would have PITONED it a long time ago, since I had to do different coding.
And restrains just what I have with mine will have to first fill up ONNX, and then I'll be stuck with the porting.
Although at the moment there are definitely some things I can teach with existing architectures/models/algorithms and port to the terminal.
Are you going to watch soccer with a beer?
Yeah, no... soccer doesn't really catch on, I like racing, and billiards, and I like to watch and play
yeah, that's it.)
I've been playing a few instruments, it won't do you any good. If you do not know how to cook.
And what, you already know what a max pooling? )
Yeah, no... soccer doesn't really catch on, I like racing, and billiards, I like to watch and play.
And what, you already know what max pooling is? )
I know about max pooling, but there was an introductory lesson today.
there's their picture processing and video, but it's not hard to transfer to time series
+ Yes, I would have PITONED for a long time, since I had to code in different ways.
And it's holding me back just the fact that I'll have to replenish ONNX with mine first, and then I'll be stuck with porting as well.
Although at the moment there's definitely something to teach the established architectures/models/algorithms and port it to the terminal.
Well, 3 people already support ONNX (including me), maybe someone else will come along
Well, three people are already in favor of ONNX (including me), maybe someone else will come along
I'm for ONNX too. I am beginning to realize that the topic of news trading can not be raised without MO.
In short, I checked the euro m5 on all instruments that I have in mt
The data is presented in a normalized sliding window of size 5, it turned out 230 signs
Each signal has its own name in each position like "XAUUSD1" .... "XAUUSD5"
I preselected the signs using the "Boruta" algorithm
it only put 25 good ones
list of good ones
Importance diagram for the selection
trained Forest on selected attributes
Accuracy : 0.6892
a list of important attributes for the model (the most important of the selected)
that's it... I thought it would be brighter
What is USDDKK ? ))
What is USDDKK ? ))
Ahahaha ))) Danish krone rules the euro )))