Show HN: Python SDK – forecasting with foundation time-series and tabular models

[ChernovAndrei]

We’ve built a Python SDK for running inference on foundation models designed for time-series and tabular data. They are new SOTA models for time-series and tabular tasks and work out of the box. They do not require model training or feature engineering. The link to the GitHub repository is: https://github.com/S-FM/faim-python-client

[srean]

I will always advise "start simple"

https://news.ycombinator.com/item?id=46055919

[anshumankmr]

>We have successfully replaced thousands of complicated deep net time series based anomaly detectors at a FANG with statistical (nonparametric, semiparametric) process control ones.

They use 3 to 4 orders lower number of trained parameters and have just enough complexity that a team of 3 or four can handle several thousands of such streams.

Could you explain how ? Cause I am working on this essentially right now and it seems management is wanting to go the way of Deep NNs for our customers.

[SubiculumCode]

I do not understand how time series can be forecast without training on data from a relevant domain. Like, would these be able to predict EEG/fMRI timeseries?

[armcat]

The promise is similar to LLMs, if you pretrain on sufficiently large timeseries datasets with sufficiently large variance/characteristics, that you will be able to transfer the model to a completely different use case that exhibits somewhat similar characteristics (in latent space). But it’s always good to check what kind of data the model was trained on, eg Chronos 2.0 training data is described in Appendix A Table 6 here: https://arxiv.org/pdf/2510.15821

[bvan]

Isn’t this the ultimate black box? If a forecasting system is a black box, then you have no chance of understanding why its performance might deteriorate. Once that happens it essentially becomes a digital paper-weight.

[OutOfHere]

That's not a good argument because it's like saying that an LLM is a black box, yet we use them all day every day. The two share the same engineering and operating principles.

[clickety_clack]

If these worked we would have heard a lot more about them.

[smallnix]

Before picking this I would benchmark on my existing data using e.g. https://unit8co.github.io/darts/index.html#regression-models

[kavalg]

It looks like this is an SaaS with an open source client only right?

[OutOfHere]

Moreover, some of the models used as listed at https://faim.it.com/models are open models developed by third-parties, and how you host and call them is up to you.

[anshumankmr]

How does next-token prediction work for time series data?

[ChernovAndrei]

There is no single answer, because there are multiple architectures for foundation time-series models, such as T5, decoder-only models, and state-space models (SSMs).

For Chronos-2 (the current state of the art in time-series modeling), the setup is almost identical to that of LLMs because it is based on the T5 architecture. The main difference is that, in time-series models, tokens correspond to subintervals in the real-valued (ℝ) space. You can check the details here: https://arxiv.org/pdf/2510.15821

[BobSonOfBob]

Would be good if the site had a couple of case studies

[chwzr]

How does it compare to tabpfn?

[ChernovAndrei]

Limix outperforms tabpfn v2: https://arxiv.org/pdf/2509.03505