AutoGluon-TimeSeries: AutoML for Probabilistic Time Series Forecasting

Code

• github.com/autogluon/autogluon
  OfficialIn paperpytorch★ 10,137
• github.com/awslabs/autogluon
  mxnet★ 10,140
• github.com/davidpicard/homm
  pytorch★ 41

Abstract

We introduce AutoGluon-TimeSeries - an open-source AutoML library for probabilistic time series forecasting. Focused on ease of use and robustness, AutoGluon-TimeSeries enables users to generate accurate point and quantile forecasts with just 3 lines of Python code. Built on the design philosophy of AutoGluon, AutoGluon-TimeSeries leverages ensembles of diverse forecasting models to deliver high accuracy within a short training time. AutoGluon-TimeSeries combines both conventional statistical models, machine-learning based forecasting approaches, and ensembling techniques. In our evaluation on 29 benchmark datasets, AutoGluon-TimeSeries demonstrates strong empirical performance, outperforming a range of forecasting methods in terms of both point and quantile forecast accuracy, and often even improving upon the best-in-hindsight combination of prior methods.

Tasks

Reproductions