SalesforceAIResearch/uni2ts

Unified Training of Universal Time Series Forecasting Transformers

58
/ 100
Established

This library helps data scientists and machine learning engineers accurately predict future trends using time series data. You input historical data, and it outputs predictions for what will happen next. It's designed for anyone needing to forecast quantities over time, such as sales, stock prices, or sensor readings.

1,436 stars.

Use this if you need a robust, pre-trained model to make accurate predictions on diverse time series datasets without extensive custom model development.

Not ideal if you're a business user looking for a point-and-click solution or don't have experience with Python and machine learning frameworks.

time-series-forecasting predictive-analytics demand-planning financial-modeling operations-forecasting
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

1,436

Forks

191

Language

Jupyter Notebook

License

Apache-2.0

Last pushed

Jan 29, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SalesforceAIResearch/uni2ts"

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