A hybrid linear-neural model for time series forecasting

Marcelo C. Medeiros, Álvaro Veiga

Research output: Contribution to journalArticlepeer-review

Abstract

This paper considers a linear model with time varying parameters controlled by a neural network to analyze and forecast nonlinear time series. We show that this formulation, called neural coefficient smooth transition autoregressive (NCSTAR) model, is in close relation to the threshold autoregressive (TAR) model and the smooth transition autoregressive (STAR) model with the advantage of naturally incorporating linear multivariate thresholds and smooth transitions between regimes. In our proposal, the neural-network output is used to induce a partition of the input space, with smooth and multivariate thresholds. This also allows the choice of good initial values for the training algorithm.

Original languageEnglish (US)
Pages (from-to)1402-1412
Number of pages11
JournalIEEE Transactions on Neural Networks
Volume11
Issue number6
DOIs
StatePublished - 2000
Externally publishedYes

Keywords

  • Neural networks
  • Nonlinear time series analysis
  • Piecewise linear models

ASJC Scopus subject areas

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'A hybrid linear-neural model for time series forecasting'. Together they form a unique fingerprint.

Cite this