Machine learning in trading: theory, models, practice and algo-trading - page 3396

[alcoloid]

Good afternoon everyone!

Is there any way to generate a new synthetic time series from a sample time series?

Help, who has encountered it)

[mytarmailS]

alcoloid #:

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)

What characteristics should match?

[Renat Akhtyamov]

alcoloid #:

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%.

[Maxim Dmitrievsky]

Looks like some yummy stuff - googles linked kozul to calibration

https://github.com/google/empirical_calibration?tab=readme-ov-file

[Maxim Dmitrievsky]

What a sodbuster

[Maxim Dmitrievsky]

https://www.cambridge.org/core/elements/causal-factor-investing/9AFE270D7099B787B8FD4F4CBADE0C6E?utm_source=hootsuite&utm_medium=twitter&utm_campaign=Elements_Economics_October_IOC

[Aleksey Nikolayev]

Maxim Dmitrievsky #:
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.

[Maxim Dmitrievsky]

Aleksey Nikolayev #:

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 seems more and more that he is not a manager at all, but just teaches students :) Takes hot MO topics and presents them as the latest developments in trading

[Aleksey Nikolayev]

Maxim Dmitrievsky #:
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

There was a claim somewhere that he was a manager of a cool fund (for a very short time) just so that the fund could legally use some of his patents - a kind of acquisition method. The question about the specific benefit of such an acquisition (cool algorithm or PR) was not discussed there.

[Maxim Dmitrievsky]

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?