Model selection and randomization for weakly dependent time series forecasting

Abstract : Observing a stationary time series, we propose in this paper new two steps procedures for predicting the next value of the time series. Following machine learning theory paradigm, the first step consists in determining randomized estimators, or "experts", in (possibly numerous) different predictive models. In the second step estimators are obtained by model selection or randomization associated with exponential weights of these experts. We prove Oracle inequalities for both estimators and provide some applications for linear, artificial Neural Networks and additive non-parametric predictors.
Document type :
Conference papers
Complete list of metadatas

Cited literature [12 references]  Display  Hide  Download

https://hal.inria.fr/inria-00386733
Contributor : Conférence Jds2009 <>
Submitted on : Friday, May 22, 2009 - 9:16:57 AM
Last modification on : Wednesday, May 15, 2019 - 3:46:34 AM
Long-term archiving on : Thursday, June 10, 2010 - 11:40:09 PM

File

p229.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00386733, version 1

Citation

Pierre Alquier, Olivier Wintenberger. Model selection and randomization for weakly dependent time series forecasting. 41èmes Journées de Statistique, SFdS, Bordeaux, 2009, Bordeaux, France, France. ⟨inria-00386733⟩

Share

Metrics

Record views

1739

Files downloads

4197