thuml/Autoformer

About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

51
/ 100
Established

This project helps operations managers, economists, energy traders, traffic planners, and public health officials predict future trends from historical data. It takes in various time-series data, such as energy consumption, traffic flow, economic indicators, weather patterns, or disease incidence, and outputs accurate long-term forecasts. This is designed for professionals who need reliable predictions to make informed decisions across different industries.

2,426 stars. No commits in the last 6 months.

Use this if you need to accurately forecast long-term trends in critical time-series data across domains like energy, traffic, economics, weather, or public health.

Not ideal if you are looking for short-term forecasts or need to analyze data that isn't sequential or time-dependent.

energy-forecasting traffic-prediction economic-modeling weather-forecasting disease-outbreak-prediction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

2,426

Forks

495

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/thuml/Autoformer"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.