Machine learning in trading: theory, models, practice and algo-trading - page 3080
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
Lilitha, today is a special day, a heightened day.
Some people have really stood out here today, and me, too.
Everyone has their own point of view, and until the points of view do not coincide, opponents may not understand each other.
Everyone has their own point of view, and until the points of view coincide, opponents may not understand each other.
If you do, why are you arguing?
Hello, people!
Hello, people!
Greetings, human!
However, bots may take offence at such a greeting :)
If I understood you correctly, you think that there are hidden diamonds in the CodeBase archive that traders just don't see? And you want to sift them out with ML?
If it is so, why think that those who wrote and published these indicators have not already shown them at their best?
By this I mean that you don't need to look for indicators, but you can look for original ideas.
How do you propose to automate the process of searching for original ideas?
I am just suggesting to find an indicator, expecting that there may be an interesting idea that works on the market, and then it can be adapted or made analogues, developed.
Greetings, human!
However, bots may take offence at such a greeting :)
You want to be tolerant? Don't be.
But in general, who knows where the salt lies... It may be in the indicators, but it's not in the park. I'm using Natashki Mashka, and it's fine.
I had a fight with chat today, he says I'm very intolerant.You want to be tolerant? I don't.
I don't even know if it's possible to tolerate bots with flaws.....
AI masters, the phone is pre-top, the moon is just kapets, in real life it is extremely sharp, AI camera made it like a crescent moon) visually there is a new moon, very beautiful.
Yeah, I saw it today. I liked it.
I want to revisit the article https://arxiv.org/pdf/2201.12692.pdf because of the off the charts fashionability of causal inference in the ME.
So, what I got out of the article.
The author, taking one of the most famous algorithms of MO -RF, analysed the changes in the error, changing the way of input data formation and the sample size. At the same time he divided the error into variance and bias, which, in his opinion, can be added up. The bias is shown in the figure in relation to some ideal, which is not clear where it came from.
The article concludes, not the first fresh conclusion, that cross-fitting is best, with folds at least as large as full sampling.
But this is not the main thing that prompted the writing.
This article is a perfect illustration of advertising promotion of trivial results.
The very title "Causal Effects" pokes our noses into our backwardness, because studying various sines we did not realise that this is the result of Causal Effects from feeding input data to the sin input and getting the result.
The author takes RF, gives input data to the input and gets an error as a result.
To make everyone realise that we are dealing with a whole new direction in MO, then the input data (predictors) are called covariates, the RF algorithm is called a meta learner, and the whole process is called Causal Effects.
The apologists of Causal Effects are not aware that sometimes in Russian covariates are those predictors that have an effect not only on the target variable but also on neighbouring predictors, i.e. the term should be used more precisely to avoid ambiguity.
Calling the RF algorithm a "meta learner" is another publicity stunt in Causal Effects, since this algorithm produces rules is certainly NOT a learner. But from an advertising point of view in machine learning there should be learners and for the importance of "meta" and basta.
The paper justifies in some detail the choice of RF as the base algorithm, specifically stating that any (?) MO algorithm can be used instead ofRF. As a generalisation of this thought, the term nuisance, i.e. unpleasant, obnoxious, annoying , is used. If by text, it should probably be translated as "a function of noise", i.e. the RF algorithm is a "function of noise". But how intricate and beautiful it sounds, and most importantly the reader, who previously thought that RF produces rules with some error, just enjoys it.
We can continue, but the above is enough to refer all this Causal Effects to pure advertising, by the way very successful, when the real nonsense sold and got a place as a professor at Stanford University, got followers who want to keep up with the new advanced trends.
So who is the author of the supposed newest cutting edge trend in ME? Judging by the number of references, one Victor Chernozhukov, a man who has no profile education, graduated from an agricultural institute in the early 90s. I remember this time very well, when millions of Chernozhukovs, under the cries of unclouded consciousness with education and facts, ran and moved all kinds of nonsense. and many of them became billionaires and top politicians.
Today the whole world lives according to the laws of advertising, all spheres, thought that MO will pass this cup. Well, no.