Machine learning in trading: theory, models, practice and algo-trading - page 1219
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
Well, that's what they call it.
Well, that's what you call it.
I'd say we've had enough...
A_K2, hi, why don't you leave here?))) keep it up...
:))) Man, this theme can't go on forever, can it? After all, in terms of attendance, beats even my branch - but the result is 0. Help the suffering, it hurts to watch. Even the Teacher left here - it turned out more profitable to sell cars...
:))) Man, this theme can't go on forever, can it? After all, in terms of attendance, beats even my branch - but the use 0.
Well, it's older. 1st post -Alexey Burnakov2016.05.26 13:32
:))) Man, this theme can't go on forever, can it? After all, in terms of attendance, beats even my branch - but the result is 0. Help the suffering, it hurts to watch. Even the teacher left here - it turned out more profitable to sell cars...
It takes 7 years to build a decent business... it takes about the same amount of time to study neurons and all the crap from scratch and apply it to kotirams ))
It takes 7 years to build a normal business... to study neurons and all the crap from scratch and apply it to quoters about the same amount of time ))
Max, we're not talking about you - about the topicstarter, about Doc, about Misha-Teacher, Sanych... No one knows how many of them there are... They've been using NS for 10 years! It's impossible to watch them without tears.
It takes 7 years to build a normal business... it takes about the same amount of time to learn neurons and all the crap from scratch and apply it to quoters ))
Well, that's a wiggle room. One year is enough for everything.
The auxiliary tasks of trading can be solved by NS already now. But you want everything at once. It is hardly possible to make a Mercedes right away, without having built at least Zaporozhets).
I don't want to be a publicist like sanych but I will tell the truth, R is the best language for research, only a pathetic theorist who has never touched it would argue with that....
Yes, Max is right, it's an analogue, and you know whatYuriy Asaulenko? It's just one R lib, and there are thousands of libs for all trends and tastes.
For example you can
download quotes through one lib
Make the spectrum analysis through a second library.
perform technical analysis via a third one
Do data mining in the fourth one
do text mining of tweets or Facebook or a web site or any text, with the fifth
combine it all into a model (neuronics, scaffolding, boosts, svm, nmm, take your pick) and optimize, crosvalidate through the sixth libu let the same Caret
and test in the strategy tester in the seventh lib
+ the richest and most advanced visualization
And all this in one language in one code, and all this fit into 50-100 lines of readable code....
What the fuck...scikit-learn, wake upYuriy Asaulenko, you have no idea what you're talking about.
Actually I know what I'm talking about.)
You should get acquainted with the subject before making conclusions.) Start by installing Anaconda on your computer - it's a ready-made Python, with everything you need to get started. And when you get the hang of it a bit, you'll probably understand the difference between modeling and ersatz modeling in R. It's like singing and sniffing.)
As long as you don't understand it. Like, if you haven't seen another car, Zaporozhets VO! car.
However, it is possible that for your tasks R is quite enough for you.
I am lying on the sofa, studying https://scikit-learn.org/stable/user_guide.html. It is so cool. ))
For those who have not yet read it, I strongly recommend it.
Zy SanSanychev R rests, and nervously smokes in the hallway. It is pathetic. ((
"BSD license".
San Sanychev R is problematic to use in sales. :-)
F-measure, R-accuracy, Increase in concentration and other stuff...
So separately each measure is incomplete, so I want to combine the two into one. The result I will use to create a model for selecting models, which on a number of features should continue to function in the future.