Welcome to TFB’s documentation!

TFB is an open-source library designed for time series forecasting researchers.

We provide a clean codebase for end-to-end evaluation of time series forecasting models, comparing their performance with baseline algorithms under various evaluation strategies and metrics.

The below figure provides a visual overview of TFB’s pipeline. You can access the source code on GitHub and read our paper on arXiv. Additionally, We have created a leaderboard for time series forecasting, which can be accessed by clicking here.

The table below provides a visual overview of how TFB’s key features compare to other libraries for time series forecasting.

GET STARTED:

• Introduction
• Quick Start

DOCUMENTATION:

• API Reference

TUTORIAL:

• Develop your own method
• Evaluate your own time series
• Steps to get the model’s predicted values and the target values

SUPPORT:

• Citation
• FAQ
• Acknowledgement
• Contact