Machine learning in trading: theory, models, practice and algo-trading - page 3396
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
Good afternoon everyone!
Is there any way to generate a new synthetic time series from a sample time series?
Help, who has encountered it)
Good afternoon everyone!
Is there any way to generate a new synthetic time series from a sample time series?
Help if anyone has encountered it)
Good afternoon everyone!
Is there any way to generate a new synthetic time series from a sample time series?
Help, who has encountered it)
if there is a descendant, your synthetic is a regular copy of it
you should first think about the meaning of the event and get to the point
and you'll still get a function that copies the original series.
There's no new bike here, 100%.Looks like some yummy stuff - googles linked kozul to calibration
https://github.com/google/empirical_calibration?tab=readme-ov-file
What a sodbuster
h ttps:// www.cambridge.org/core/elements/causal-factor-investing/9AFE270D7099B787B8FD4F4CBADE0C6E?utm_source=hootsuite&utm_medium=twitter&utm_campaign=Elements_Economics_October_IOC
In general, it is not a bad text, clarifying and ordering a lot of things, although there are some theoretical snags.
Imho, from a practical point of view, the task of separating real associative links from apparent ones (stable from unstable) is more relevant for us.
Overall not a bad text, clarifying and organising a lot of things, although there are some theoretical snags.
Imho, from a practical point of view, the task of separating real associative links from apparent ones (stable from unstable) is more relevant for us.
It's looking more and more like he's not a manager at all, he's just teaching students :) He takes hot MO topics and presents them as the latest achievements in trading
I would like to write an optimiser for a portfolio of models, since they are generated quite quickly, on an industrial scale
But if we get a lot of them, we don't want to drag and drop them all into the terminal. purely hypothetically, if we save not models, but stack the datasets on which they are trained, and then train one final model on them, the results should be comparable to the ensemble of models, right?