Machine learning in trading: theory, models, practice and algo-trading - page 3040
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
Are there any options? ))))
Why are you always asking questions...
What's cool is that the analysis itself and the picture are done in R))
a community of ass-kicking E.I. geeks
1 In an article (or just a page of the site) you can see at once what place in the material you want to pay attention to. Video cannot boast of this.
2 Text is easier to translate into any language. (And the translation text is perceived at once, but you need to listen to the whole voice).
3 You can copy part of the code from the text for experiments.
a community of ass-kicking E.I. geeks
There is no one to listen to on this channel except Redozubov
Has anyone tried DMwR::SMOTE?
Aligns classes using the nearest neighbours algorithm, i.e. it adds "similar" predictor values rather than duplicating them.
https://medium.com/nuances-of-programming/smote-метод-увеличения-числа-примеров-миноритарного-класса-da91a62f9914
Has anyone tried DMwR::SMOTE?
It aligns classes using nearest neighbours algorithm, i.e. it adds "similar" predictor values instead of duplicating them.
I tried that a long time ago.
Is it worth the trouble? Or should I go with upSample?
Is it worth it? Or should I go with upSample?
It's worth comparing.
It's not clear how to compare. UpSample should lead to overtraining due to duplication of identical data, which is not immediately detectable.