AutoGluon–TimeSeries: AutoML for Probabilistic Time Series Forecasting

Oleksandr Shchur, Ali Caner Turkmen, Nick Erickson, Huibin Shen, Alexander Shirkov, Tony Hu, Bernie Wang
Proceedings of the Second International Conference on Automated Machine Learning, PMLR 224:9/1-21, 2023.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v224-shchur23a, title = {AutoGluon–TimeSeries: AutoML for Probabilistic Time Series Forecasting}, author = {Shchur, Oleksandr and Turkmen, Ali Caner and Erickson, Nick and Shen, Huibin and Shirkov, Alexander and Hu, Tony and Wang, Bernie}, booktitle = {Proceedings of the Second International Conference on Automated Machine Learning}, pages = {9/1--21}, year = {2023}, editor = {Faust, Aleksandra and Garnett, Roman and White, Colin and Hutter, Frank and Gardner, Jacob R.}, volume = {224}, series = {Proceedings of Machine Learning Research}, month = {12--15 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v224/shchur23a/shchur23a.pdf}, url = {https://proceedings.mlr.press/v224/shchur23a.html}, 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.} }
Endnote
%0 Conference Paper %T AutoGluon–TimeSeries: AutoML for Probabilistic Time Series Forecasting %A Oleksandr Shchur %A Ali Caner Turkmen %A Nick Erickson %A Huibin Shen %A Alexander Shirkov %A Tony Hu %A Bernie Wang %B Proceedings of the Second International Conference on Automated Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Aleksandra Faust %E Roman Garnett %E Colin White %E Frank Hutter %E Jacob R. Gardner %F pmlr-v224-shchur23a %I PMLR %P 9/1--21 %U https://proceedings.mlr.press/v224/shchur23a.html %V 224 %X 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.
APA
Shchur, O., Turkmen, A.C., Erickson, N., Shen, H., Shirkov, A., Hu, T. & Wang, B.. (2023). AutoGluon–TimeSeries: AutoML for Probabilistic Time Series Forecasting. Proceedings of the Second International Conference on Automated Machine Learning, in Proceedings of Machine Learning Research 224:9/1-21 Available from https://proceedings.mlr.press/v224/shchur23a.html.

Related Material