Machine learning in trading: theory, models, practice and algo-trading - page 2351
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
A certain Prado wrote here that MO is better than statistics )
I looked at his first book (Russian translation) a little bit and selectively. I got the opposite impression, that the whole book is pure matstat)
In the preface he writes that alone will not work. So urgently unite into a team, study the book and become billionaires)
I looked at his first book (the Russian translation) a little and selectively. I got the opposite impression, that the whole book is pure matstat)
In the preface he writes that one alone will not work. So urgently unite into a team, learn the book and become billionaires)
The fusion of the two types of codes is in fact very similar, but only in python, ers are left out.
Alexei, what is your programming language?
Alexey, what is your programming language?
mql5
mql5
And research, IO, statistics, also mql5 ?
mql5
I support)
And research, IO, statistics, also mql5?
If you look at the idea, R - there are just much more of them implemented than in python. If the idea is useful and it's possible, then I write it in mql5 - for example, somewhere on this forum I posted Kolmogorov-Smirnov test. If the idea is absolutely unaffordable to rewrite it on mql5, then I simply don't consider it working - lest it be like in that joke about a smart plane - "now let's try to fly with all this". When ONNX support will appear - it will be possible to expand the range of used ideas.
If you look at the idea, R - there are just much more implemented than in python. If the idea is useful and it's possible, then I write it in mql5 - for example, somewhere on this forum I posted Kolmogorov-Smirnov test. If the idea is absolutely unaffordable to rewrite it on mql5, then I simply don't consider it working - lest it be like in that joke about a smart plane - "now let's try to fly with all this". When ONNX support will appear - it will be possible to expand the range of ideas used.
Thanks...
Absolutely adequate/optimal use of languages, each to his own purpose...
If you look at the idea, R - there are just much more implemented than in python. If the idea is useful and it's possible, then I write it in mql5 - for example, somewhere on this forum I posted Kolmogorov-Smirnov test. If the idea is absolutely unaffordable to rewrite it on mql5, then I simply don't consider it working - lest it be like in that joke about a smart plane - "now let's try to fly with all this". When ONNX support will appear - you'll be able to expand the range of used ideas.
Exactly! "...check or drive?"
https://neurohive.io/ru/frameworki/google-otkryli-frejmvork-dlya-avtomaticheskogo-poiska-arhitektury-ml-modelej/
Exactly! "...Check or drive?"
https://neurohive.io/ru/frameworki/google-otkryli-frejmvork-dlya-avtomaticheskogo-poiska-arhitektury-ml-modelej/
What's the use of this autoML? There have been such libraries for many years...
You have to work with attributes and kinds of information representation, but they're all rubbish with it.