neuralforecast
Time series forecasting suite using deep learning models
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later.
- PyTorch and PyTorch Lightning are heavy dependencies; GPU support is optional but recommended for training speed.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
Apache-2.0 (permissive) — Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most production and research applications.
last release 2026-08-04 (10 days) · last repo commit 2026-08-10 · 4,237 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 317,327 downloads/mo, #7,662 on PyPI
Alternatives
Verify before relying
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()- 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
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 on this page. Verify before relying on it.
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
neuralforecast on PyPI
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.
Requires Python 3.10 or later. PyTorch and PyTorch Lightning are heavy dependencies; GPU support is optional but recommended for training speed.
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()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 the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 11 packagescoreforecastfsspecnumpypandasscipytorchtornadopytorch-lightningrayoptunautilsforecast |
| Maintenance | Actively maintained 10 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 317,327 / month, #7,662 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseNatural Language :: EnglishProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: neuralforecast-3.2.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “neural time series forecasting”
- neuralforecastNeuralForecast provides a collection of neural network models for…
- neuralprophetNeuralProphet is a PyTorch-based framework for interpretable time…
- dartsDarts provides forecasting and anomaly detection for time series…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also mlforecast · neuralprophet · nixtla · pytorch-forecasting · statsforecast · coreforecast · hierarchicalforecast · utilsforecast · skforecast · datasetsforecast