GluonTS: Probabilistic Time Series Models in Python
Published in
arXiv.org(2019)External Links:
TL
TL;DR
Gluon Time Series is introduced, a library for deep-learning-based time series modeling that provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating model accuracy.
Abstract
We introduce Gluon Time Series (GluonTS, available at this https URL), a library for deep-learning-based time series modeling. GluonTS simplifies the development of and experimentation with time series models for common tasks such as forecasting or anomaly detection. It provides all necessary components and tools that scientists need for quickly building new models, for efficiently running and analyzing experiments and for evaluating model accuracy.
References48 items
1
The Sockeye 2 Neural Machine Translation Toolkit at AMTA 2020
2
Deep Factors for Forecasting
3
Probabilistic Forecasting with Spline Quantile Function RNNs
4
Deep Factors with Gaussian Processes for Forecasting
5