Ensembles of recurrent neural networks for robust time series forecasting

DOI:	https://doi.org/10.1007/978-3-319-71078-5_3
URL:	https://link.springer.com/chapter/10.1007/978-3-31...
Additional URL:	http://www.heikopaulheim.com/docs/sgai_2017.pdf
Document Type:	Conference or workshop publication
Year of publication:	2017
Book title:	Artificial Intelligence XXXIV : 37th SGAI International Conference on Artificial Intelligence, AI 2017, Cambridge, UK, December 12-14, 2017, proceedings
The title of a journal, publication series:	Lecture Notes in Computer Science
Volume:	10630
Page range:	34-46
Conference title:	SGAI International Conference on Artificial Intelligence
Location of the conference venue:	Cambridge, UK
Date of the conference:	12.-14.12.2017
Publisher:	Bramer, Max
Place of publication:	Berlin [u.a.]
Publishing house:	Springer
ISBN:	978-3-319-71077-8 , 978-3-319-71078-5
ISSN:	0302-9743 , 1611-3349
Publication language:	English
Institution:	School of Business Informatics and Mathematics > Information Systems V: Web-based Systems (Bizer 2012-) School of Business Informatics and Mathematics > Web Data Mining (Juniorprofessur) (Paulheim 2013-2017)
Subject:	004 Computer science, internet
Abstract:	Time series forecasting is a problem that is strongly dependent on the underlying process which generates the data sequence. Hence,finding good model fits often involves complex and time consuming tasks such as extensive data preprocessing, designing hybrid models, or heavy parameter optimization. Long Short-Term Memory (LSTM), a variant of recurrent neural networks (RNNs), provide state of the art forecasting performance without prior assumptions about the data distribution. LSTMs are, however, highly sensitive to the chosen network architecture and parameter selection, which makes it difficult to come up with a one-size-fits-all solution without sophisticated optimization and parameter tuning. To overcome these limitations, we propose an ensemble architecture that combines forecasts of a number of differently parameterized LSTMs to a robust final estimate which, on average, performs better than the majority of the individual LSTM base learners, and provides stable results across different datasets. The approach is easily parallelizable and we demonstrate its effectiveness on several real-world data sets.