neuralforecast
A Python library offering scalable and user-friendly implementations of state-of-the-art neural forecasting models.
What is neuralforecast?
NeuralForecast is a Python library that provides a large collection of state-of-the-art neural network models for time series forecasting. It focuses on delivering scalable, accurate, and user-friendly implementations to improve forecasting pipeline efficiency and performance. The library includes models ranging from classic RNNs to the latest transformers, addressing the practical challenges of applying neural methods to forecasting tasks.
Data scientists, machine learning engineers, and researchers working on time series forecasting who need robust, production-ready neural models with support for probabilistic forecasts, exogenous variables, and automatic hyperparameter optimization.
Developers choose NeuralForecast for its extensive, battle-tested model implementations, seamless integration with the Nixtla ecosystem (like StatsForecast), and emphasis on usability without sacrificing accuracy or scalability.
Overview
Scalable and user friendly neural :brain: forecasting algorithms.
Use Cases
Best For
- Forecasting time series with complex patterns using neural networks
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
