Nixtla/neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

81
/ 100
Verified

This project helps you predict future trends and values for your business or research by analyzing past data. You provide historical time series data, and it outputs precise future forecasts using advanced neural network models. This tool is ideal for data scientists, analysts, or researchers who need accurate and scalable forecasting for various real-world applications.

4,003 stars. Used by 5 other packages. Actively maintained with 22 commits in the last 30 days. Available on PyPI.

Use this if you need to accurately forecast future values based on historical time series data, especially when dealing with large datasets or complex patterns.

Not ideal if you only need basic statistical forecasting methods or prefer not to use neural network models.

time-series-forecasting demand-planning financial-forecasting inventory-management resource-allocation
Maintenance 20 / 25
Adoption 15 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

4,003

Forks

483

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

22

Dependencies

9

Reverse dependents

5

Get this data via API

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

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