Forecasting platforms & libraries · Amazon Web Services (open source)

GluonTS

Open-source Python toolkit from AWS for building and evaluating probabilistic deep-learning forecasting models.

Visit GluonTS Alternatives

GluonTS is an open-source library, originally built by AWS research, focused specifically on probabilistic time-series forecasting with deep learning. It provides reference implementations of neural forecasting architectures such as DeepAR, Temporal Fusion Transformer and various transformer-based models, along with the data-loading, batching and probabilistic-output plumbing needed to train them, and standardized backtesting utilities for comparing models on the same evaluation protocol. It sits a level below AutoGluon-TimeSeries in abstraction: AutoGluon automates model selection on top of libraries like GluonTS, while GluonTS itself is aimed at researchers and engineers who want direct control over model architecture and training. It supports multiple deep-learning backends and is commonly used as a research baseline and building block in academic and industrial forecasting benchmarks.

At a glance

Vendor Amazon Web Services (open source)
Pricing model Open source + paid options
Free tier Yes
Deployment Self-hosted
Open source Yes (Apache-2.0)
Best for Researchers and ML engineers who want direct control over neural forecasting model architecture rather than an automated pipeline.

Pricing

Free and open source with no commercial tier.

Pricing has not been verified yet — see the vendor's site.

Features

  • Reference implementations of DeepAR, Temporal Fusion Transformer and other neural forecasters
  • Probabilistic forecasting output with distributional predictions
  • Standardized backtesting and evaluation utilities
  • Data-loading and batching pipeline for time-series training
  • Multiple deep-learning backend support
  • Used as a research baseline in forecasting benchmarks
  • Extensible model API for custom architectures

Integrations

Profile last reviewed September 21, 2026

Alternatives

PyTorch Forecasting Open-source deep-learning forecasting library built on PyTorch and PyTorch Lightning for panel/multi-series data. AutoGluon Open-source AutoML library from AWS that automates model selection and ensembling, including a time-series forecasting module. Darts Open-source Python library offering one unified API across dozens of classical, ML and deep-learning forecasting models.

GluonTS in the index now

Terms to know

Time series forecasting Predicting future values of a metric using patterns found in its own historical sequence over time. Machine learning Building models that learn patterns from data to make predictions or decisions, rather than following hand-coded rules. Predictive analytics Analytics that uses historical data and statistical models to estimate what is likely to happen next. Backtesting Testing a trading or investment strategy against historical data to see how it would have performed. Deep learning Machine learning using neural networks with many layers, able to learn complex patterns directly from raw data such as images or text.

Related guides

How to choose a forecasting platform or library Pick a time-series forecasting library by how many series you're forecasting and how much modeling control your team wants.