Discussion of article "Evaluation and selection of variables for machine learning models" - page 5
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
Drawing a simple drawing illustrating the numbers (-1, 1 (0) ????
Please read the article carefully? And next to it? And do not know how to use ZZ?
Maybe the translation is not good?
Specify more precisely your comments, please can improve English?
ZigZag This sequence does not need to be predicted at all, if you know the lag(ZigZag)=-1 ,then the ZigZag must be 1;the lag(ZigZag)=1 ,then the zigzag=-1;.
all of the lag(ZigZag) is occured at the past time,it can predict the zigzag 100% accurately. so if you know the time is zigzag point ,you can 100% accurately
predict the zigzag is -1 or 1.
But in the realtime you cannot know the time is zigzag point,so you must caculate the third status (0), so how can it work?
You can reference this right articl https://www.mql5.com/en/articles/2773.
Good afternoon.
Good afternoon.
ZZ is really not defined on the last bars (the last vertex). Neural network training is conducted on ZZ values without the last 300 bars !!!! On those bars where ZZ is defined.
You carefully look at the scripts and do not rush to conclusions. You can look stupid.
You carefully look at the scripts and do not rush to conclusions.
in the realtime ,do you use 'without the last 300 bars '!
You looks so stupid ,can you use it in the realtime.?
All of your article are wrong ,because your target define is wrong.All canot work in the realtime, as follow your point ,you singal will happen after 300 bars later.
All canot work in the realtime, as follow your point ,you singal will happened after 300 bars later.
in the realtime ,do you use 'without the last 300 bars '!
You looks so stupid ,can you use it in the realtime.?
All of your article are wrong ,because your target define is wrong.All canot work in the realtime, as follow your point ,you singal will happen after 300 bars later.
All canot work in the realtime, as follow your point ,you singal will happened after 300 bars later.
You don't really understand the author's vision, you are too naive in your own imagination, and the stupidity of what you say is just mapped on yourself, please don't embarrass your country anymore, not only stupid, but ugly.
to Vladimir Perervenko: thanks again for those wonderful articles, you did and doing really good research! this stupid thing from "freewalk", not all chinese like him.
I answered you in the next branch.
Hi Vladimir,
I did not find your answer regarding this question. I also not sure what is the value of Dig. could you plz specify. thank you!
Dear all,
Can someone tell me what the --Dig-- defined in ZZ function variable means. Is it a constant? if yes what should the value be of this constant?
Dig - the number of digits after the decimal point in quotes. Maybe 5 or 3.
I'm sorry to be late with the reply. Did not see the question. The discussion is scattered across many branches. I do not have time to track it.
Excuse me.
The article is voluminous, thanks for the labour.
However, it is questionable:
1. using stratification with a selected target that is labelled on each bar. Mixing two unrepresentative samples usually improves the result, which skews it.
2- Feature selection based on constructed models, especially given the first split randoms and the greedy method, is more of a feature reduction method for the model building method. The greedy method is not always correct and stable. In this case, perhaps you need to use different subsamples, at least.
I didn't understand the second method until the end - is it the same with a random first predictor, and then we try to build a leaf or we build a tree and leave the best leaf, which is used for evaluation?