[wuj]

On a related note, Amazon also had a model for time series forecasting called Chronos.

https://github.com/amazon-science/chronos-forecasting

[claytonjy]

And like all deep learning forecasting models thus far, it makes for a nice paper but is not worth anyone using for a real problem. Much slower than the classical methods it fails to beat.

[p1esk]

That’s what people said about CV models in 2011.

[claytonjy]

That's fair, but they stopped saying it about CV models in 2012. We've been saying this about foundational forecasting models since...2019 at least, probably earlier. But it is a harder problem!

[belter]

They also have Amazon Forecast with different algos - https://aws.amazon.com/forecast/

[toasted-subs]

Something I've had issues with time series has been having to use relatively custom models.

It's difficult to use off the shelf tools when starting with math models.