Zero-Shot Time Series Forecasting with TabPFNv2
- 27-05-2025: 📝 New paper version and v1.0.0 release! Strong GIFT-EVAL results, new AutoSeasonalFeatures, improved CalendarFeatures.
- 27-01-2025: 🚀 Ranked 1st on GIFT-EVAL benchmark[1]!
- 10-10-2024: 🚀 TabPFN-TS paper accepted to NeurIPS 2024 TRL and TSALM workshops!
[1] Last checked on: 10/03/2025
We demonstrate that the tabular foundation model TabPFNv2, combined with lightweight feature engineering, enables zero-shot time series forecasting for both point and probabilistic tasks. On the GIFT-EVAL benchmark, our method achieves performance on par with top-tier models across both evaluation metrics.
Our work proposes to frame univariate time series forecasting as a tabular regression problem.
Concretely, we:
- Transform a time series into a table
- Extract features and add them to the table
- Perform regression on the table using TabPFNv2
- Use regression results as time series forecasting outputs
For more details, please refer to our paper.
- Zero-shot forecasting: this method is extremely fast and requires no training, making it highly accessible for experimenting with your own problems.
- Point and probabilistic forecasting: it provides accurate point forecasts as well as probabilistic forecasts.
- Support for exogenous variables: if you have exogenous variables, this method can seemlessly incorporate them into the forecasting model.
On top of that, thanks to tabpfn-client from Prior Labs, you won't even need your own GPU to run fast inference with TabPFNv2. 😉 We have included tabpfn-client as the default engine in our implementation.
You can install the package via pip:
pip install tabpfn-time-seriesTo install the package in editable mode with all development dependencies, run the following command in your terminal:
pip install -e ".[dev]"
# or with uv
uv pip install -e ".[dev]"The demo should explain it all. 😉
