← all repositories

Nixtla/statsforecast

A Python library for lightning-fast univariate time series forecasting using classical statistical and econometric models.

4.8k stars Python ML FrameworksDomain Apps
statsforecast
Velocity · 7d
+2.9
★ / day
Trend
steady
star history

StatsForecast provides a collection of widely used univariate time series forecasting models including automatic ARIMA, ETS, CES, and Theta modeling. It is optimized for high performance and includes models like MSTL, AutoETS, AutoARIMA, and naive baselines. The library targets data scientists and analysts needing efficient forecasting at scale.

heatdrop uses Google Analytics to see which pages get read — nothing else. Your call. How we handle data.