What it does
PyTorch Forecasting is a library for time series forecasting, which means predicting future values from data recorded over time.
It handles messy real-world data, comes with several modern neural network models, and shows how each prediction was made. It can train on ordinary processors or graphics cards.
It also helps tune model settings automatically and draw charts of predictions against real results.
Who it's for
Data scientists and researchers who build forecasting models.
Can I use it without coding?
Developers only. It's a Python code library. New to this? Start here.
Can I run it?
- Cost
- FreeNothing to pay or sign up for.
- Runs on
- Windows, Mac, Linux
- Computer
- An ordinary computer is fine
- Privacy
- Runs on your own device: your data stays with you
- API key
- Not needed
Try it
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (MIT): Very permissive: free to use, change and share, including for business.
- More on staying safe
Where people are talking about it
- PatchTST: A Time Series is Worth 64 WordsResearch paper · Nov 2022
- N-HiTS: Neural Hierarchical Interpolation for Time Series ForecastingResearch paper · Jan 2022
- Temporal Fusion Transformers for Interpretable Multi-horizon Time Series ForecastingResearch paper · Dec 2019
- N-BEATS: Neural basis expansion analysis for interpretable time series forecastingResearch paper · May 2019