Dynamical local models for segmentation and prediction of financial time series


In the analysis and prediction of many real-world time series, the assumption of stationarity is not valid. A special form of non-stationarity, where the underlying generator switches between (approximately) stationary regimes, seems particularly appropriate for financial markets. We introduce a new model which combines a dynamic switching (controlled by a hidden Markov model) and a non-linear dynamical system. We show how to train this hybrid model in a maximum likelihood approach and evaluate its performance on both synthetic and financial data.

Publication DOI: https://doi.org/10.1080/13518470110071155
Divisions: ?? 50811700Jl ??
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: This is a preprint of an article submitted for consideration in the European Journal of Finance © 2001 copyright Taylor & Francis; European Journal of Finance is available online at: http://www.informaworld.com/openurl?genre=article&issn=1351-847X&volume=7&issue=4&spage=289
Uncontrolled Keywords: NCRG
Publication ISSN: 1466-4364
Last Modified: 27 Jun 2024 07:36
Date Deposited: 11 Aug 2009 10:47
Full Text Link:
Related URLs: http://www.info ... sue=4&spage=289 (Publisher URL)
PURE Output Type: Article
Published Date: 2001
Authors: Azzouzi, M
Nabney, Ian T. (ORCID Profile 0000-0003-1513-993X)



Version: Accepted Version

Export / Share Citation


Additional statistics for this record