Tools for non-linear time series forecasting in economics - an empirical comparison of regime switching vector autoregressive models and recurrent neural networks

Binner, JM, Elger, T, Nilsson, B and Tepper, JA ORCID logoORCID: https://orcid.org/0000-0001-7339-0132, 2004. Tools for non-linear time series forecasting in economics - an empirical comparison of regime switching vector autoregressive models and recurrent neural networks. In: Binner, JM, Kendall, G and Chen, S-H, eds., Applications of artificial intelligence in finance and economics. Advances in econometrics (19). Leeds: Emerald, pp. 71-91. ISBN 9780762311507

[thumbnail of 196509_553 Tepper PostPrint.pdf]
Preview
Text
196509_553 Tepper PostPrint.pdf

Download (223kB) | Preview

Abstract

The purpose of this study is to contrast the forecasting performance of two non-linear models, a regime-switching vector autoregressive model (RS-VAR) and a recurrent neu-ral network (RNN), to that of a linear benchmark VAR model. Our specific forecasting experiment is UK inflation and we utilize monthly data from 1969-2003. The RS-VAR and the RNN perform approximately on par over both monthly and annual forecast hori-zons. Both non-linear models perform significantly better than the VAR model. Keywords: Inflation forecasting, regime-switching vector autoregressive model, recurrent neural network.

Item Type: Chapter in book
Creators: Binner, J.M., Elger, T., Nilsson, B. and Tepper, J.A.
Publisher: Emerald
Place of Publication: Leeds
Date: 2004
Number: 19
ISBN: 9780762311507
ISSN: 0731-9053
Identifiers:
Number
Type
10.1016/S0731-9053(04)19003-8
DOI
Rights: © 2004 Emerald Group Publishing Limited.
Divisions: Schools > School of Science and Technology
Record created by: EPrints Services
Date Added: 09 Oct 2015 11:00
Last Modified: 08 Feb 2024 11:40
URI: https://irep.ntu.ac.uk/id/eprint/21476

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year