---
id: neuralforecast
version: "3.2.1"
license: Apache-2.0
license_treatment: permissive
maintenance: active
---

# neuralforecast — Time series forecasting suite using deep learning models

License: permissive · Maintenance: active · Downloads: 317.3K/mo

## What it is and what it does

NeuralForecast is a library of neural network models for time series forecasting, built on PyTorch and PyTorch Lightning. It implements over 30 architectures ranging from classic RNNs and LSTMs to modern Transformers like Informer and iTransformer, as well as specialized models like NBEATS and NHITS. The library emphasizes usability through a familiar sklearn-style interface (.fit and .predict) and integrates with utilsforecast and coreforecast for data handling and visualization.

The package supports exogenous variables, static covariates, probabilistic forecasting with quantile losses, and automatic hyperparameter tuning via Ray and Optuna. It includes built-in interpretability methods for trend, seasonality, and exogenous components. The library is actively maintained, includes official implementations of published research (NHITS from AAAI 2023, NBEATSx from International Journal of Forecasting), and supports modern Python versions (3.10–3.13).

Use it for:

- Train and deploy NBEATS or NHITS models for univariate time series forecasting with minimal code
- Incorporate exogenous variables like weather or prices into neural forecasts using built-in support
- Automatically tune hyperparameters across multiple models using Ray or Optuna integration
- Build probabilistic forecasts with quantile losses or parametric distributions for uncertainty quantification
- Apply transfer learning to forecast new series with little historical data

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

NeuralForecast provides a collection of neural network models for time series forecasting, including RNNs, LSTMs, Transformers, and specialized architectures like NBEATS and NHITS, with sklearn-like fit/predict syntax.

Yes. NeuralForecast is worth installing for time series forecasting projects that need modern neural architectures with production-ready usability. It has active maintenance, no known vulnerabilities, permissive licensing, and low install friction. The main consideration is the substantial dependency footprint (PyTorch, Lightning, Ray, Optuna) and Python 3.10+ requirement; if your environment already supports these or you need the advanced models it provides, the tradeoff is justified.

## Install

pip install neuralforecast
uv add neuralforecast
poetry add neuralforecast

## Installing neuralforecast

Before you install: Low install friction with a pure-Python wheel. Active maintenance with a recent release (10 days old) and 4237 repository stars. Requires 11 runtime dependencies including PyTorch, PyTorch Lightning, Ray, and Optuna, which are substantial but standard for neural forecasting work.

License in practice: Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most production and research applications.

Quickstart:

pip install neuralforecast

from neuralforecast import NeuralForecast
from neuralforecast.models import NBEATS
from neuralforecast.utils import AirPassengersDF

nf = NeuralForecast(
    models=[NBEATS(input_size=24, h=12, max_steps=100)],
    freq='ME'
)
nf.fit(df=AirPassengersDF)
nf.predict()

Requires Python 3.10 or later. PyTorch and PyTorch Lightning are heavy dependencies; GPU support is optional but recommended for training speed.

Verify before relying:

- Whether GPU acceleration is required or optional for typical forecasting tasks
- Performance benchmarks comparing these models to statistical baselines on standard datasets
- Memory footprint and training time for different model architectures on typical time series

## Package facts

- License: Apache-2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 317.3K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

neural time series forecasting, deep learning forecasting models, NBEATS LSTM transformer forecasting, time series prediction pytorch, automated forecasting with neural networks, time-series-forecasting, deep-learning, neural-networks

[View on SkillFed](https://skillfed.io/packages/neuralforecast) · [View on PyPI](https://pypi.org/project/neuralforecast/)