Machine learning in trading: theory, models, practice and algo-trading - page 2646
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
As I understand it, this is a modification of what is usually done when building a decision tree. At each step, a variable is searched for and a piece that can be bitten from it - they call it peeling. From all such possible steps they choose those that build an "optimal trajectory" - the dependence of the average target on the number of remaining points. The trajectory is also used to determine the moment when the algorithm stops (when there is no noticeable improvement when the box is reduced).
The approach is interesting first of all because it shows that tree building algorithms can and should be modified.
I see data cleaning, but no mention of the tree construction method, which, let's say, is modified. So you're assuming that after data cleaning, the tree is simply built. Is it built by splits from boxes - by their limits or what is not included in the box is replaced by zeros (or another variable aggregating such states)?
2645 (two thousand six hundred and forty-fifth !!!) page. Active participants still plan to get together to start something to demonstrate in the future the possibility to show something different from 50/50 not in tester :-)
Actually there is a lot to do, in terms of code - I just don't have enough energy for all the ideas, that's why everything is slow.
I see data cleansing, but no mention of a way to build a tree that is, say, modified. So you assume that after data cleaning the tree is simply built. Is it built by splits from boxes - by their limits or what is not included in the box is replaced by zeros (or another variable aggregating such states)?
It seems quite normal to me that a simple algorithm only works on a limited portion of the set of predictors.
You could do a step-by-step removal from the sample of what falls into the "good" boxes and apply the algorithm to the remainder. In essence, it would be similar to bousting. Probably, you can do it similarly to randomforest - take a large set of predictors and for each subset find several boxes.
Use the method of one writer who became a writer because he could not find a book interesting for himself and just wrote one).
https://www.mql5.com/ru/blogs/post/746398
You just can't get behind the scenes, only what you can write here.
wai !
I understand you, you have special education and experience, unlike "activists"... (you have economics and professional experience in divorce centres, right?)
but how many times can you make fun of them?
wai !
I understand you, you have special education and experience, unlike "activists".... (you have economics and professional experience in divorce centres?).
but how many times can you make fun of them?
And why such aggression? Nobody owes you anything here, people are communicating on the topic, maybe they will write 2000 pages more, it's their right.
wai !
I understand you, you have special education and experience, unlike "activists".... (you have economics and professional experience in divorce centres?).
but how many times can you make fun of them?