kwuking/TimeMixer

[ICLR 2024] Official implementation of "TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting"

49
/ 100
Emerging

This helps professionals who need to predict future values based on historical data, like sales managers forecasting product demand or energy analysts predicting consumption. You input a time series dataset, and it provides accurate forecasts for both short and long periods. This tool is for anyone who relies on data-driven predictions to make informed decisions and optimize operations.

1,889 stars. No commits in the last 6 months.

Use this if you need highly accurate, multi-scale forecasts for time series data, ranging from short-term predictions to extended future horizons.

Not ideal if your primary need is simple trend analysis without requiring complex decomposition or multi-scale predictive modeling.

predictive-analytics demand-forecasting operations-planning financial-modeling resource-management
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,889

Forks

223

Language

Python

License

Apache-2.0

Last pushed

Oct 05, 2025

Commits (30d)

0

Get this data via API

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

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