functime-org/functime

Time-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.

43
/ 100
Emerging

This tool helps data analysts and quantitative researchers efficiently forecast future trends and extract meaningful insights from large collections of time-series data. You input historical time-series data, and it outputs predictions for future values and calculated features that describe patterns within your data. This is ideal for anyone managing many related time series, like stock prices, product sales, or sensor readings.

1,167 stars. No commits in the last 6 months.

Use this if you need to generate fast, accurate forecasts and extract descriptive features across hundreds or thousands of individual time series simultaneously.

Not ideal if you only work with a single time series or require highly specialized, domain-specific forecasting models that aren't available out-of-the-box.

quantitative-analysis financial-forecasting demand-planning operations-analytics predictive-maintenance
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

1,167

Forks

62

Language

Python

License

Apache-2.0

Last pushed

Oct 04, 2025

Commits (30d)

0

Get this data via API

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

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