# Nixtla/statsforecast

Lightning ⚡️ fast forecasting with statistical and econometric models.

Repository: https://github.com/Nixtla/statsforecast
Canonical: https://ross.abutalabs.com/products/statsforecast
Homepage: https://nixtlaverse.nixtla.io/statsforecast
Language: Python
License: Apache-2.0
License Family: permissive
Topics: time-series, statistics, forecasting, arima, econometrics, machine-learning, python, exponential-smoothing, ets, baselines, predictions, naive, seasonal-naive, fbprophet, prophet, neuralprophet, mstl, theta, automl, data-science
Last push: 2026-08-26T22:30:12+00:00

## Health v2 (maintenance only)
Score: 93/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 81, longevity 100
- inputs: {"age_days": 1744, "days_push": 7, "days_rel": 48, "gap_med": 75.5, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4887, forks 385 (observed 2026-08-28T04:09:01.901764+00:00)

## What it is
StatsForecast is a Python library providing fast, scalable implementations of statistical and econometric univariate time series forecasting models such as AutoARIMA, AutoETS, AutoCES, MSTL, and Theta. It supports probabilistic forecasting, anomaly detection, exogenous variables, and distributed execution on Spark, Dask, and Ray with a familiar sklearn-like fit/predict API.

## Use cases
- forecast sales or demand across millions of time series
- fit automatic ARIMA models faster than pmdarima or statsmodels
- generate prediction intervals and probabilistic forecasts
- detect anomalies in time series data
- benchmark forecasting models like naive, seasonal naive, and ETS
- replace Prophet with a faster statistical alternative
- run distributed forecasting on Spark, Dask, or Ray clusters
- perform time series cross-validation and model selection

## When to choose
- you need fast, accurate univariate statistical forecasting at scale
- you want sklearn-style fit/predict syntax for many time series
- you need prediction intervals, conformal prediction, or anomaly detection
- you want to benchmark against naive and seasonal baselines
- you need distributed forecasting across large datasets

## When to avoid
- you need deep learning or neural forecasting models (use NeuralForecast instead)
- you need multivariate forecasting with cross-series dependencies
- you work outside the Python ecosystem
- you need a hosted foundation-model forecasting API (consider TimeGPT)

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, data-science, benchmarking
- domain: time-series, data-science, machine-learning
- platform: python
- tags: forecasting, arima, ets, exponential-smoothing, theta, mstl, probabilistic-forecasting, anomaly-detection, distributed-computing, spark, dask, ray, sklearn-api

## Member repositories
- Nixtla/statsforecast (main) score 93

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.901764+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:18:13.100360+00:00, confidence not recorded.
  - readme: https://github.com/Nixtla/statsforecast (fetched 2026-08-28T04:09:01.901764+00:00, sha b49f471c9cb3)
  - homepage: https://nixtlaverse.nixtla.io/statsforecast (fetched 2026-08-29T09:00:40.779555+00:00, sha 1b169a30e2ff)
  - site_page: https://nixtla.io/docs (fetched 2026-08-29T09:00:40.789245+00:00, sha 109f5713c50b)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/getting-started/introduction.html (fetched 2026-08-29T09:00:40.791129+00:00, sha 5ec741ca6918)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/getting-started/installation.html (fetched 2026-08-29T09:00:40.793045+00:00, sha 3dfd967af041)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/getting-started/getting_started_short.html (fetched 2026-08-29T09:00:40.794995+00:00, sha d3e3ae35ad22)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/getting-started/getting_started_complete.html (fetched 2026-08-29T09:00:40.796905+00:00, sha c71364636074)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/getting-started/getting_started_complete_polars.html (fetched 2026-08-29T09:00:40.799263+00:00, sha e0bcb740c4a4)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/tutorials/anomalydetection.html (fetched 2026-08-29T09:00:40.801551+00:00, sha a2b55267422f)
  - site_page: https://nixtlaverse.nixtla.io/statsforecast/docs/tutorials/conformalprediction.html (fetched 2026-08-29T09:00:40.803356+00:00, sha 50fafb482178)
- Data as of 2026-08-30T08:39:29.467469+00:00.