Time Series Tutorial

TabPFN can be used for time series forecasting by framing it as a tabular regression problem. This tutorial demonstrates how to use the TabPFN Time Series package for accurate zero-shot forecasting. It was developed by Shi Bin Hoo, Samuel Müller, David Salinas and Frank Hutter.

Quick Start

First, install the package:

!git clone https://github.com/liam-sbhoo/tabpfn-time-series.git
!pip install -r tabpfn-time-series/requirements.txt

See the demo notebook for a complete example.

How It Works

TabPFN performs time series forecasting by:

1. Converting time series data into a tabular format
2. Extracting temporal features (trends, seasonality, etc.)
3. Using TabPFN's regression capabilities for prediction
4. Converting predictions back to time series format

This approach provides several benefits:

• Zero-shot forecasting: No training required - just fit and predict
• Both point and probabilistic forecasts: Get confidence intervals with your predictions
• Support for exogenous variables: Easily incorporate external factors
• Fast inference: Uses tabpfn-client for GPU-accelerated predictions

Additional Resources

• GitHub Repository
• Research Paper

Getting Help

Join our Discord community for support and discussions about TabPFN time series forecasting.