Model selection in online learning for times series forecasting
Authors: Jamil, W. and Bouchachia, A.
Journal: Advances in Intelligent Systems and Computing
Volume: 840
Pages: 83-95
ISSN: 2194-5357
DOI: 10.1007/978-3-319-97982-3_7
Abstract:This paper discusses the problem of selecting model parameters in time series forecasting using aggregation. It proposes a new algorithm that relies on the paradigm of prediction with expert advice, where online and offline autoregressive models are regarded as experts. The desired goal of the proposed aggregation-based algorithm is to perform not worse than the best expert in the hindsight. The theoretical analysis shows that the algorithm has a guarantee that holds for any data sequence. Moreover, the empirical evaluation shows that the algorithm outperforms other popular model selection criteria such as Akaike and Bayesian information criteria on cyclic behaving time series.
https://eprints.bournemouth.ac.uk/30875/
Source: Scopus
Model Selection in Online Learning for Times Series Forecasting
Authors: Jamil, W. and Bouchachia, A.
Journal: ADVANCES IN COMPUTATIONAL INTELLIGENCE SYSTEMS (UKCI)
Volume: 840
Pages: 83-95
eISSN: 2194-5365
ISBN: 978-3-319-97981-6
ISSN: 2194-5357
DOI: 10.1007/978-3-319-97982-3_7
https://eprints.bournemouth.ac.uk/30875/
Source: Web of Science (Lite)
Model Selection in Online Learning for Times Series Forecasting
Authors: Jamil, W. and Bouchachia, A.
Conference: 18th Annual UK Workshop on Computational Intelligence
Dates: 5-7 September 2018
https://eprints.bournemouth.ac.uk/30875/
Source: Manual
Preferred by: Hamid Bouchachia
Model Selection in Online Learning for Times Series Forecasting.
Authors: Bouchachia, A.
Conference: UKCI 2018: 18th Annual UK Workshop on Computational Intelligence
Abstract:This paper discusses the problem of selecting model parameters in time series forecasting using aggregation. It proposes a new algorithm that relies on the paradigm of prediction with expert advice, where online and offline autoregressive models are regarded as experts. The desired goal of the proposed aggregation-based algorithm is to perform not worse than the best expert in the hindsight. The theoretical analysis shows that the algorithm has a guarantee that holds for any data sequence. Moreover, the empirical evaluation shows that the algorithm outperforms other popular model selection criteria such as Akaike and Bayesian information criteria on cyclic behaving time series.
https://eprints.bournemouth.ac.uk/30875/
Source: BURO EPrints