# Nixtla/neuralforecast

Scalable and user friendly neural :brain: forecasting algorithms.

Repository: https://github.com/Nixtla/neuralforecast
Canonical: https://ross.abutalabs.com/products/neuralforecast
Homepage: https://nixtlaverse.nixtla.io/neuralforecast
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, forecasting, esrnn, nbeats, nbeatsx, time-series, pytorch, transformer, nhits, neural-network, machine-learning, deep-neural-networks, deepar, tft, robust-regression, hierarchical-forecasting, probabilistic-forecasting, baselines, baselines-zoo, hint
Last push: 2026-08-24T14:10:45+00:00

## Health v2 (maintenance only)
Score: 98/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 96, longevity 100
- inputs: {"age_days": 1956, "days_push": 9, "days_rel": 29, "gap_med": 26, "n_releases_24m": 20}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4257, forks 499 (observed 2026-08-28T04:08:40.575555+00:00)

## What it is
NeuralForecast is a Python library offering a large collection of state-of-the-art neural forecasting models (NBEATS, NHITS, TFT, PatchTST, DeepAR, LSTM, transformers, and more) built on PyTorch. It provides a unified sklearn-like fit/predict interface with support for exogenous variables, probabilistic forecasting, and automatic hyperparameter selection.

## Use cases
- forecast future sales or demand with neural networks
- train NBEATS or NHITS on multiple time series
- generate probabilistic forecasts with quantile intervals
- forecast time series with exogenous variables like prices or weather
- automatically tune and select the best forecasting model
- benchmark deep learning models against statistical baselines

## When to choose
- you need deep learning models for time series forecasting in Python
- you want a simple unified API across many neural forecasting architectures
- you need probabilistic or quantile forecasts
- you have many related time series and want global models with cross-learning

## When to avoid
- you only need simple statistical methods like ARIMA or ETS
- you cannot use PyTorch or lack GPU resources for large-scale training
- you need a hosted foundation-model API rather than training your own models

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science, sdk
- domain: machine-learning, deep-learning, data-science, time-series
- platform: python, cross-platform
- tags: time-series, forecasting, pytorch, nbeats, nhits, transformer, probabilistic-forecasting, exogenous-variables, hyperparameter-tuning, gpu

## Member repositories
- Nixtla/neuralforecast (main) score 98

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:40.575555+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 2026-08-29T18:22:06.986968+00:00, confidence not recorded.
  - readme: https://github.com/Nixtla/neuralforecast (fetched 2026-08-28T04:08:40.575555+00:00, sha 52fa7e5dc4fe)
  - homepage: https://nixtlaverse.nixtla.io/neuralforecast (fetched 2026-08-29T09:11:50.998145+00:00, sha efe7209a4824)
  - site_page: https://nixtla.io/docs (fetched 2026-08-29T09:11:51.007110+00:00, sha 109f5713c50b)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/getting-started/quickstart.html (fetched 2026-08-29T09:11:51.009194+00:00, sha 2b7cd5f67dc9)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/getting-started/installation.html (fetched 2026-08-29T09:11:51.011092+00:00, sha f606223af302)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/getting-started/datarequirements.html (fetched 2026-08-29T09:11:51.012748+00:00, sha 556f53776410)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/overview.html (fetched 2026-08-29T09:11:51.014512+00:00, sha 2810bd5d7d66)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/objectives.html (fetched 2026-08-29T09:11:51.016241+00:00, sha a7d8bf457f78)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/exogenous_variables.html (fetched 2026-08-29T09:11:51.017769+00:00, sha a7a2f7636dfd)
  - site_page: https://nixtlaverse.nixtla.io/neuralforecast/docs/capabilities/categorical_features.html (fetched 2026-08-29T09:11:51.019730+00:00, sha 4396c3fe2f5e)
- Data as of 2026-08-30T08:39:29.467469+00:00.