Nixtla / neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.
https://nixtlaverse.nixtla.io/neuralforecast
Apache License 2.0
2.98k stars 342 forks source link

Update models in the README #946

Closed candalfigomoro closed 4 months ago

candalfigomoro commented 6 months ago

Add missing models to the README file:

CLAassistant commented 6 months ago

CLA assistant check
All committers have signed the CLA.

CLAassistant commented 6 months ago

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

candalfigomoro commented 6 months ago

Should we also add Time-LLM? HINT?

cchallu commented 6 months ago

Thanks for this! We should wait a few days; we are adding the iTransformer and MLPMultivariate. Can you also add them once they are in the main branch?

jmoralez commented 5 months ago

I think we can move forward with this now and add BiTCN (#958).

candalfigomoro commented 5 months ago

Added more models:

Not sure about what to do with HINT, since it basically wraps other models.

TiDE can also be added when merged.

jmoralez commented 4 months ago

We just merged DeepNPTS (#990)

candalfigomoro commented 4 months ago

@jmoralez Added

candalfigomoro commented 4 months ago

@elephaint I think HINT is the only missing one. It's a little bit special. It should be multivariate but probabilistic forecast (!), no point forecast, yes Auto, exog depends on the base model. Structure also depends on the base model.

elephaint commented 4 months ago

@elephaint I think HINT is the only missing one. It's a little bit special. It should be multivariate but probabilistic forecast (!), no point forecast, yes Auto, exog depends on the base model. Structure also depends on the base model.

Agree, that's a bit an odd one. I'm playing with more of these types of weird ones, so it's still on my list. I think maybe a 'meta-model' category would make sense sometime.