Maxim Dmitrievsky #: New from Google, TSMixer, seems to be superior to TimeGPT in benchmarks, just started reading.
I need good probabilistic forecasting for series, but not as cheesy as it is nowadays (quantile regression, for example). I didn't see anything about it in the article itself, although the list of references seems to contain some information on this topic.
We need a good probabilistic forecasting for series, but not as cheesy as it is nowadays (quantile regression, for example). I didn't see anything about it in the article itself, although there is some literature on this topic in the list of references.
I think there are some Python libs, I'll try to cook something up, I can't say anything yet ).
What kind of error can be attributed to the spread? This seemingly stupid problem does not give me a rest. If a model works well with a low spread, but when the spread is increased, it is worse. What exactly to fix? :) or how to train it to trade with a large spread. It would seem: make trades longer. But it doesn't work. I seem to put it in, but it is not fixed.
What kind of error is this, how can I get it out?
I put it in and out, I put it in the signs and rearrange the target ones. It still doesn't work.
Maxim Dmitrievsky #: What kind of error can be attributed to the spread? This seemingly stupid problem does not give me a rest. If a model works well with a low spread, but when the spread is increased, it is worse. What exactly to fix? :) or how to train it to trade with a large spread. It would seem: make trades longer. But it doesn't work. I seem to put it in, but it is not fixed.
What kind of this error, how to get it out?
I put it in and out, I put it in the signs and rearrange the target ones. It's still not the same.
The spread is not an error.
It's a problem of formulating the target: there is no spread in increments between asks and increments between bits.
Allow the use of cookies to log in to the MQL5.com website.
Please enable the necessary setting in your browser, otherwise you will not be able to log in.
You are signed in. Two-factor authentication has been disabled. Set it up again and scan a new QR code, or continue with two-factor authentication disabled.
New from Google, TSMixer, seems to be superior to TimeGPT in benchmarks, just started reading.
I need good probabilistic forecasting for series, but not as cheesy as it is nowadays (quantile regression, for example). I didn't see anything about it in the article itself, although the list of references seems to contain some information on this topic.
We need a good probabilistic forecasting for series, but not as cheesy as it is nowadays (quantile regression, for example). I didn't see anything about it in the article itself, although there is some literature on this topic in the list of references.
https://www.r-bloggers.com/2023/12/be-part-of-the-global-r-community/?utm_source=phpList& utm_medium=email&utm_campaign=R-bloggers-daily&utm_content=HTML
I go to mechmat, I see girls sitting there.
If I don't go to the lecture, I'll lose my erection.
https://www.r-bloggers.com/2023/12/be-part-of-the-global-r-community/?utm_source=phpList& utm_medium=email&utm_campaign=R-bloggers-daily&utm_content=HTML
Sanych, what do you have to do with this post?
It's just a link to the R hangouts.
R is a whole universe.... and we're on the sidelines.
What kind of error can be attributed to the spread? This seemingly stupid problem does not give me a rest. If a model works well with a low spread, but when the spread is increased, it is worse. What exactly to fix? :) or how to train it to trade with a large spread. It would seem: make trades longer. But it doesn't work. I seem to put it in, but it is not fixed.
The spread is not an error.
It's a problem of formulating the target: there is no spread in increments between asks and increments between bits.
Simple, a link to the R hangouts.
R is a whole universe.... and we're on the sidelines.
So get involved, do something useful, show the universe.