Chronos-forecasting is a zero-shot time series forecasting framework based on a pretrained large language model. It enables the prediction of future values across diverse datasets without requiring task-specific training or optimization.
Die Hauptfunktionen von amazon-science/chronos-forecasting sind: LLM-Based Forecasting, Probabilistic Forecasting, Zero-Shot Forecasting, Probabilistic Generative Sampling, Supervised Model Weight Optimization, Dynamic Covariate Integration, Time Series Model Tuning, Uncertainty Estimation.
Open-Source-Alternativen zu amazon-science/chronos-forecasting sind unter anderem: awslabs/gluon-ts — GluonTS is a framework for probabilistic time series forecasting, designed to predict future values as probability… awslabs/gluonts — GluonTS is a probabilistic time series library and deep learning forecasting framework. It provides a toolkit for… google-research/timesfm — TimesFM is a time series foundation model designed to generalize across diverse temporal datasets for forecasting and… unit8co/darts — Darts is a Python time series library designed for forecasting, anomaly detection, and the preprocessing of univariate… autogluon/autogluon — AutoGluon is an automated machine learning framework and multimodal library designed to automate the end-to-end… sktime/pytorch-forecasting — PyTorch Forecasting is a deep learning framework designed for building and training neural network architectures…
GluonTS is a framework for probabilistic time series forecasting, designed to predict future values as probability distributions with confidence intervals. It supports both traditional model training and zero-shot forecasting, where pretrained models generate predictions for new series without additional training. The project distinguishes itself by integrating a wide variety of forecasting approaches into a unified workflow. This includes deep learning architectures such as recurrent neural networks and causal convolutions, as well as the integration of external statistical models, the Proph
GluonTS is a probabilistic time series library and deep learning forecasting framework. It provides a toolkit for building, training, and evaluating neural network architectures that predict future values as probability distributions to quantify uncertainty. The project distinguishes itself by supporting zero-shot forecasting and integrating diverse modeling approaches, including deep probabilistic neural networks and wrappers for external statistical libraries such as Prophet and R forecast. It implements specialized architectural primitives like causal convolutions and invertible residual n
TimesFM is a time series foundation model designed to generalize across diverse temporal datasets for forecasting and anomaly detection. It functions as a pretrained model for predicting future values in univariate time series data, eliminating the need for manual training from scratch. The project includes a framework for adapting pretrained weights to specific datasets using low-rank adaptation to improve accuracy. It also provides specialized capabilities for integrating time-series predictions as tools within autonomous AI agent architectures and automated workflows. The system supports
Darts is a Python time series library designed for forecasting, anomaly detection, and the preprocessing of univariate and multivariate temporal data. It serves as a comprehensive framework for training and evaluating a wide range of statistical, machine learning, and deep learning models to predict future numerical values. The toolkit is distinguished by its support for global time series modeling, allowing a single model to be trained across multiple different series to leverage shared patterns. It also features a hierarchical time series manager to ensure consistency between aggregate and