# Advice for Time Series Forcasting

**URL:** https://discourse.pymc.io/t/advice-for-time-series-forcasting/16393
**Category:** version agnostic
**Tags:** time\_series
**Created:** [January 16, 2025, 2:55pm UTC](https://discourse.pymc.io/t/advice-for-time-series-forcasting/16393 "2025-01-16T14:55:10Z")
**Posts on this page:** 1
**Showing post:** 11

<div class="post-metadata">

### Author: ![jessegrabowski](https://yyz2.discourse-cdn.com/flex036/user_avatar/discourse.pymc.io/jessegrabowski/32/5010_2.png) [@jessegrabowski](https://discourse.pymc.io/u/jessegrabowski)
#### Post date: [January 23, 2025, 3:27am UTC](https://discourse.pymc.io/t/advice-for-time-series-forcasting/16393/11 "2025-01-23T03:27:19Z")

</div>

I recently did an AR model with student-T innovations [using pm.CustomDist](https://www.pymc.io/projects/examples/en/latest/time_series/Time_Series_Generative_Graph.html) on a panel of several thousand timeseries and it fit in a reasonable time (\<=1hr). For simple models (e.g. no hidden states) this is where I’d start.

I think Prophet is still a really good general starting point. I go through [an implementation here](https://discourse.pymc.io/t/best-practices-for-time-series-forecasting/12232/4), and there’s also an [example notebook](https://www.pymc.io/projects/examples/en/latest/time_series/Air_passengers-Prophet_with_Bayesian_workflow.html). Neither goes into how to do hierarchy, but it’s just y = X\beta, so you’ll just be doing the usual indexing tricks for regression models. If you go that route and get stuck, don’t hesitate to make a thread asking for help.

---

_[View the full topic](https://discourse.pymc.io/t/advice-for-time-series-forcasting/16393)._